BibSLEIGH — Proceedings of the 36th International Conference on Machine Learning

Kamalika Chaudhuri, Ruslan Salakhutdinov
Proceedings of the 36th International Conference on Machine Learning
ICML, 2019.

KER

@proceedings{ICML-2019,
	editor        = "Kamalika Chaudhuri and Ruslan Salakhutdinov",
	ee            = "http://proceedings.mlr.press/v97/",
	publisher     = "{PMLR}",
	series        = "{Proceedings of Machine Learning Research}",
	title         = "{Proceedings of the 36th International Conference on Machine Learning}",
	volume        = 97,
	year          = 2019,
}

Contents (774 items)

ICML-2019-AbbatiWO0SB: AReS and MaRS Adversarial and MMD-Minimizing Regression for SDEs (GA, PW, MAO, AK0, BS, SB), pp. 1–10.
ICML-2019-AbelsRLNS #learning #multi: Dynamic Weights in Multi-Objective Deep Reinforcement Learning (AA, DMR, TL, AN, DS), pp. 11–20.
ICML-2019-Abu-El-HaijaPKA #architecture #graph #higher-order #named: MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing (SAEH, BP, AK, NA, KL, HH, GVS, AG), pp. 21–29.
ICML-2019-AcharyaCT: Communication-Constrained Inference and the Role of Shared Randomness (JA, CLC, HT), pp. 30–39.
ICML-2019-AcharyaSFS #communication #distributed #learning #sublinear: Distributed Learning with Sublinear Communication (JA, CDS, DJF, KS), pp. 40–50.
ICML-2019-AcharyaS #communication #complexity #estimation: Communication Complexity in Locally Private Distribution Estimation and Heavy Hitters (JA, ZS), pp. 51–60.
ICML-2019-AdamsJWS #fault #learning #metric #modelling: Learning Models from Data with Measurement Error: Tackling Underreporting (RA, YJ, XW, SS), pp. 61–70.
ICML-2019-AdelW #approach #learning #named #visual notation: TibGM: A Transferable and Information-Based Graphical Model Approach for Reinforcement Learning (TA, AW), pp. 71–81.
ICML-2019-AdigaKMRV: PAC Learnability of Node Functions in Networked Dynamical Systems (AA, CJK, MM, SSR, AV), pp. 82–91.
ICML-2019-Agarwal #automation: Static Automatic Batching In TensorFlow (AA), pp. 92–101.
ICML-2019-AgarwalBCHSZZ #adaptation #performance: Efficient Full-Matrix Adaptive Regularization (NA, BB, XC, EH, KS, CZ, YZ), pp. 102–110.
ICML-2019-AgarwalBHKS #online: Online Control with Adversarial Disturbances (NA, BB, EH, SMK, KS), pp. 111–119.
ICML-2019-AgarwalDW #algorithm: Fair Regression: Quantitative Definitions and Reduction-Based Algorithms (AA, MD, ZSW), pp. 120–129.
ICML-2019-AgarwalLS0 #learning: Learning to Generalize from Sparse and Underspecified Rewards (RA, CL, DS, MN0), pp. 130–140.
ICML-2019-AgrawalTHB #interactive #kernel #performance: The Kernel Interaction Trick: Fast Bayesian Discovery of Pairwise Interactions in High Dimensions (RA, BLT, JHH, TB), pp. 141–150.
ICML-2019-AhmedR0S #comprehension #optimisation #policy: Understanding the Impact of Entropy on Policy Optimization (ZA, NLR, MN0, DS), pp. 151–160.
ICML-2019-AivodjiAFGHT #named: Fairwashing: the risk of rationalization (UA, HA, OF, SG, SH, AT), pp. 161–170.
ICML-2019-AkimotoSYUSN #adaptation #architecture #probability: Adaptive Stochastic Natural Gradient Method for One-Shot Neural Architecture Search (YA, SS, NY, KU, SS, KN), pp. 171–180.
ICML-2019-AkrourP0N #algorithm #approximate #policy: Projections for Approximate Policy Iteration Algorithms (RA, JP, JP0, GN), pp. 181–190.
ICML-2019-AlaaS #modelling #validation: Validating Causal Inference Models via Influence Functions (AMA, MvdS), pp. 191–201.
ICML-2019-AlbuquerqueMDCF #generative #multi #network: Multi-objective training of Generative Adversarial Networks with multiple discriminators (IA, JM, TD, BC, THF, IM), pp. 202–211.
ICML-2019-AletJVRLK #adaptation #graph #memory management #network: Graph Element Networks: adaptive, structured computation and memory (FA, AKJ, MBV, AR, TLP, LPK), pp. 212–222.
ICML-2019-AllenH #comprehension #towards #word: Analogies Explained: Towards Understanding Word Embeddings (CA, TMH), pp. 223–231.
ICML-2019-AllenSST #infinity #learning #prototype: Infinite Mixture Prototypes for Few-shot Learning (KRA, ES, HS, JBT), pp. 232–241.
ICML-2019-Allen-ZhuLS #convergence #learning: A Convergence Theory for Deep Learning via Over-Parameterization (ZAZ, YL, ZS), pp. 242–252.
ICML-2019-AlviRCRO #optimisation: Asynchronous Batch Bayesian Optimisation with Improved Local Penalisation (ASA, BXR, JPC, SJR, MAO), pp. 253–262.
ICML-2019-AminKMV #bound #difference #privacy #trade-off: Bounding User Contributions: A Bias-Variance Trade-off in Differential Privacy (KA, AK, AMM, SV), pp. 263–271.
ICML-2019-AnconaOG #algorithm #approximate #network #polynomial: Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Value Approximation (MA, CÖ, MHG), pp. 272–281.
ICML-2019-AndertonA #approach #scalability: Scaling Up Ordinal Embedding: A Landmark Approach (JA, JAA), pp. 282–290.
ICML-2019-AnilLG #approximate #sorting: Sorting Out Lipschitz Function Approximation (CA, JL, RBG), pp. 291–301.
ICML-2019-AntelmiARL #analysis #multi #semistructured data: Sparse Multi-Channel Variational Autoencoder for the Joint Analysis of Heterogeneous Data (LA, NA, PR, ML), pp. 302–311.
ICML-2019-ArazoOAOM #modelling: Unsupervised Label Noise Modeling and Loss Correction (EA, DO, PA, NEO, KM), pp. 312–321.
ICML-2019-AroraDHLW #analysis #fine-grained #network #optimisation: Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks (SA, SSD, WH, ZL0, RW), pp. 322–332.
ICML-2019-AssadiBM #composition #distributed #random: Distributed Weighted Matching via Randomized Composable Coresets (SA, MB, VSM), pp. 333–343.
ICML-2019-AssranLBR #distributed #learning #probability: Stochastic Gradient Push for Distributed Deep Learning (MA, NL, NB, MR), pp. 344–353.
ICML-2019-AstudilloF #optimisation: Bayesian Optimization of Composite Functions (RA, PIF), pp. 354–363.
ICML-2019-AtasuM #approximate #distance: Linear-Complexity Data-Parallel Earth Mover's Distance Approximations (KA, TM), pp. 364–373.
ICML-2019-AwanKRS #exponential #functional: Benefits and Pitfalls of the Exponential Mechanism with Applications to Hilbert Spaces and Functional PCA (JA, AK, MR, ABS), pp. 374–384.
ICML-2019-AydoreTV #probability: Feature Grouping as a Stochastic Regularizer for High-Dimensional Structured Data (SA, BT, GV), pp. 385–394.
ICML-2019-AyedLC #behaviour #modelling #process #statistics: Beyond the Chinese Restaurant and Pitman-Yor processes: Statistical Models with double power-law behavior (FA, JL, FC), pp. 395–404.
ICML-2019-BackursIOSVW #clustering #scalability: Scalable Fair Clustering (AB, PI, KO, BS, AV, TW), pp. 405–413.
ICML-2019-BalajiHCF #approach #statistics: Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs (YB, HH, RC, SF), pp. 414–423.
ICML-2019-BalcanKT: Provable Guarantees for Gradient-Based Meta-Learning (MFB, MK, AT), pp. 424–433.
ICML-2019-BalduzziGB0PJG #game studies #learning #symmetry: Open-ended learning in symmetric zero-sum games (DB, MG, YB, WC0, JP, MJ, TG), pp. 434–443.
ICML-2019-BalinAZ #feature model #re-engineering: Concrete Autoencoders: Differentiable Feature Selection and Reconstruction (MFB, AA, JYZ), pp. 444–453.
ICML-2019-BansalLRSW #higher-order #logic #machine learning #named #proving #theorem proving: HOList: An Environment for Machine Learning of Higher Order Logic Theorem Proving (KB, SML, MNR, CS, SW), pp. 454–463.
ICML-2019-BapstSDSKBH #physics: Structured agents for physical construction (VB, ASG, CD, KLS, PK, PWB, JBH), pp. 464–474.
ICML-2019-BaranchukPSB #graph #learning #similarity: Learning to Route in Similarity Graphs (DB, DP, AS, AB), pp. 475–484.
ICML-2019-BarrosPW #memory management #personalisation #recognition: A Personalized Affective Memory Model for Improving Emotion Recognition (PVAB, GIP, SW), pp. 485–494.
ICML-2019-BartlettGHV #adaptation: Scale-free adaptive planning for deterministic dynamics & discounted rewards (PLB, VG, JH, MV), pp. 495–504.
ICML-2019-BasuGLS #classification #streaming: Pareto Optimal Streaming Unsupervised Classification (SB0, SG, BL, SS), pp. 505–514.
ICML-2019-BateniCEFMR #category theory #optimisation: Categorical Feature Compression via Submodular Optimization (MB, LC, HE, TF, VSM, AR), pp. 515–523.
ICML-2019-BatsonR #named #self: Noise2Self: Blind Denoising by Self-Supervision (JB, LR), pp. 524–533.
ICML-2019-BeatsonA #optimisation #performance #random: Efficient optimization of loops and limits with randomized telescoping sums (AB, RPA), pp. 534–543.
ICML-2019-BeckerPGZTN #network: Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spaces (PB, HP, GHWG, CZ, CJT, GN), pp. 544–552.
ICML-2019-Becker-Ehmck0S #linear: Switching Linear Dynamics for Variational Bayes Filtering (PBE, JP0, PvdS), pp. 553–562.
ICML-2019-BehpourLZ #learning #predict #probability: Active Learning for Probabilistic Structured Prediction of Cuts and Matchings (SB, AL, BDZ), pp. 563–572.
ICML-2019-BehrmannGCDJ #network: Invertible Residual Networks (JB, WG, RTQC, DD, JHJ), pp. 573–582.
ICML-2019-BelilovskyEO #learning: Greedy Layerwise Learning Can Scale To ImageNet (EB, ME, EO), pp. 583–593.
ICML-2019-BenyahiaYBJDSM #multi: Overcoming Multi-model Forgetting (YB, KY, KBS, MJ, ACD, MS, CM), pp. 594–603.
ICML-2019-BenzingGMMS #approximate #learning #realtime: Optimal Kronecker-Sum Approximation of Real Time Recurrent Learning (FB, MMG, AM, AM, AS), pp. 604–613.
ICML-2019-BertranMPQRRS #obfuscation: Adversarially Learned Representations for Information Obfuscation and Inference (MB, NM, AP, QQ, MRDR, GR, GS), pp. 614–623.
ICML-2019-BeygelzimerPSTW #algorithm #classification #linear #multi #performance: Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case (AB, DP, BS, DT, CYW, CZ), pp. 624–633.
ICML-2019-BhagojiCMC #learning #lens: Analyzing Federated Learning through an Adversarial Lens (ANB, SC, PM, SBC), pp. 634–643.
ICML-2019-BianB0: Optimal Continuous DR-Submodular Maximization and Applications to Provable Mean Field Inference (YAB, JMB, AK0), pp. 644–653.
ICML-2019-BibautMVL #evaluation #learning #performance: More Efficient Off-Policy Evaluation through Regularized Targeted Learning (AB, IM, NV, MJvdL), pp. 654–663.
ICML-2019-BiettiMCM #kernel #network: A Kernel Perspective for Regularizing Deep Neural Networks (AB, GM, DC, JM), pp. 664–674.
ICML-2019-BlauM #trade-off: Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff (YB, TM), pp. 675–685.
ICML-2019-BodaA #correlation #fault #how #online: Correlated bandits or: How to minimize mean-squared error online (VPB, PLA), pp. 686–694.
ICML-2019-BojchevskiG #graph: Adversarial Attacks on Node Embeddings via Graph Poisoning (AB, SG), pp. 695–704.
ICML-2019-BorsosCL0 #online #reduction: Online Variance Reduction with Mixtures (ZB, SC, KYL, AK0), pp. 705–714.
ICML-2019-BoseH #composition #constraints #graph: Compositional Fairness Constraints for Graph Embeddings (AJB, WLH), pp. 715–724.
ICML-2019-BouthillierLV #research: Unreproducible Research is Reproducible (XB, CL, PV), pp. 725–734.
ICML-2019-BraunPTW: Blended Conditonal Gradients (GB, SP, DT, SW), pp. 735–743.
ICML-2019-BravermanJKW #clustering #order: Coresets for Ordered Weighted Clustering (VB, SHCJ, RK, XW), pp. 744–753.
ICML-2019-BregereGGS: Target Tracking for Contextual Bandits: Application to Demand Side Management (MB, PG, YG, GS), pp. 754–763.
ICML-2019-BridgesGFVH: Active Manifolds: A non-linear analogue to Active Subspaces (RAB, ADG, CF, MEV, CH), pp. 764–772.
ICML-2019-BrookesPL #adaptation #design #robust: Conditioning by adaptive sampling for robust design (DHB, HP, JL), pp. 773–782.
ICML-2019-BrownGNN #learning: Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations (DSB, WG, PN, SN), pp. 783–792.
ICML-2019-BrownLGS: Deep Counterfactual Regret Minimization (NB, AL, SG, TS), pp. 793–802.
ICML-2019-BrunetAAZ #bias #comprehension #word: Understanding the Origins of Bias in Word Embeddings (MEB, CAH, AA, RSZ), pp. 803–811.
ICML-2019-BrutzkusGE #latency #privacy: Low Latency Privacy Preserving Inference (AB, RGB, OE), pp. 812–821.
ICML-2019-BrutzkusG #modelling #problem #why: Why do Larger Models Generalize Better? A Theoretical Perspective via the XOR Problem (AB, AG), pp. 822–830.
ICML-2019-BubeckLPR #constraints: Adversarial examples from computational constraints (SB, YTL, EP, IPR), pp. 831–840.
ICML-2019-BuchnikCHM #self: Self-similar Epochs: Value in arrangement (EB, EC, AH, YM), pp. 841–850.
ICML-2019-BunneA0J #generative #learning #modelling: Learning Generative Models across Incomparable Spaces (CB, DAM, AK0, SJ), pp. 851–861.
ICML-2019-BurtRW #convergence #process: Rates of Convergence for Sparse Variational Gaussian Process Regression (DRB, CER, MvdW), pp. 862–871.
ICML-2019-ByrdL #learning #question #what: What is the Effect of Importance Weighting in Deep Learning? (JB, ZCL), pp. 872–881.
ICML-2019-CaiLS #analysis #normalisation: A Quantitative Analysis of the Effect of Batch Normalization on Gradient Descent (YC, QL, ZS), pp. 882–890.
ICML-2019-CanGZ #convergence #linear #probability: Accelerated Linear Convergence of Stochastic Momentum Methods in Wasserstein Distances (BC, MG, LZ), pp. 891–901.
ICML-2019-CanalMDR: Active Embedding Search via Noisy Paired Comparisons (GC, AKM, MAD, CJR), pp. 902–911.
ICML-2019-CaoS #learning #multi #problem: Dynamic Learning with Frequent New Product Launches: A Sequential Multinomial Logit Bandit Problem (JC, WS), pp. 912–920.
ICML-2019-CardosoAWX #game studies #nash: Competing Against Nash Equilibria in Adversarially Changing Zero-Sum Games (ARC, JDA, HW, HX), pp. 921–930.
ICML-2019-ChaiTOG #automation: Automated Model Selection with Bayesian Quadrature (HC, JFT, MAO, RG), pp. 931–940.
ICML-2019-ChandakTKJT #learning: Learning Action Representations for Reinforcement Learning (YC, GT, JK, SMJ, PST), pp. 941–950.
ICML-2019-ChangMG #metric #scheduling #using: Dynamic Measurement Scheduling for Event Forecasting using Deep RL (CHC, MM, AG), pp. 951–960.
ICML-2019-CharoenphakdeeL #learning #on the #symmetry: On Symmetric Losses for Learning from Corrupted Labels (NC, JL, MS), pp. 961–970.
ICML-2019-ChatterjiPB #kernel #learning #online: Online learning with kernel losses (NSC, AP, PLB), pp. 971–980.
ICML-2019-ChattopadhyayMS #network #perspective: Neural Network Attributions: A Causal Perspective (AC, PM, AS, VNB), pp. 981–990.
ICML-2019-ChaudhuriK #identification #multi #probability: PAC Identification of Many Good Arms in Stochastic Multi-Armed Bandits (ARC, SK), pp. 991–1000.
ICML-2019-Chen #analysis #bound #consistency #fault #kernel #nearest neighbour: Nearest Neighbor and Kernel Survival Analysis: Nonasymptotic Error Bounds and Strong Consistency Rates (GHC), pp. 1001–1010.
ICML-2019-ChenBBGGMO #markov #monte carlo: Stein Point Markov Chain Monte Carlo (WYC, AB, FXB, JG, MAG, LWM, CJO), pp. 1011–1021.
ICML-2019-ChenDS: Particle Flow Bayes' Rule (XC, HD, LS), pp. 1022–1031.
ICML-2019-ChenFLM #clustering: Proportionally Fair Clustering (XC, BF, LL, KM), pp. 1032–1041.
ICML-2019-ChenJ #learning: Information-Theoretic Considerations in Batch Reinforcement Learning (JC, NJ), pp. 1042–1051.
ICML-2019-Chen0LJQS #generative #learning #recommendation: Generative Adversarial User Model for Reinforcement Learning Based Recommendation System (XC, SL0, HL, SJ, YQ, LS), pp. 1052–1061.
ICML-2019-ChenLCZ #comprehension #network: Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels (PC, BL, GC, SZ), pp. 1062–1070.
ICML-2019-ChenTZB00 #approach #generative #network: A Gradual, Semi-Discrete Approach to Generative Network Training via Explicit Wasserstein Minimization (YC, MT, CZ, BB, DH0, JP0), pp. 1071–1080.
ICML-2019-ChenWLW #adaptation: Transferability vs. Discriminability: Batch Spectral Penalization for Adversarial Domain Adaptation (XC, SW, ML, JW0), pp. 1081–1090.
ICML-2019-ChenW0R #algorithm #graph #incremental #performance: Fast Incremental von Neumann Graph Entropy Computation: Theory, Algorithm, and Applications (PYC, LW, SL0, IR), pp. 1091–1101.
ICML-2019-ChenXHY #named #problem #scalability: Katalyst: Boosting Convex Katayusha for Non-Convex Problems with a Large Condition Number (ZC, YX, HH, TY), pp. 1102–1111.
ICML-2019-ChenYWLYLL #multi #scalability: Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching (ZC, ZY, XW, XL, XY, GL, LL), pp. 1112–1121.
ICML-2019-ChenZBH #robust: Robust Decision Trees Against Adversarial Examples (HC, HZ0, DSB, CJH), pp. 1122–1131.
ICML-2019-ChenZWMH #named: RaFM: Rank-Aware Factorization Machines (XC, YZ, JW, WM, JH), pp. 1132–1140.
ICML-2019-ChengVOCYB #learning: Control Regularization for Reduced Variance Reinforcement Learning (RC, AV, GO, SC, YY, JB), pp. 1141–1150.
ICML-2019-ChengYRB #optimisation #policy #predict: Predictor-Corrector Policy Optimization (CAC, XY, NDR, BB), pp. 1151–1161.
ICML-2019-ChiquetRM #network #re-engineering: Variational Inference for sparse network reconstruction from count data (JC, SR, MM), pp. 1162–1171.
ICML-2019-ChitraR #random: Random Walks on Hypergraphs with Edge-Dependent Vertex Weights (UC, BJR), pp. 1172–1181.
ICML-2019-ChoiTGWE: Neural Joint Source-Channel Coding (KC, KT, AG, TW, SE), pp. 1182–1192.
ICML-2019-ChoromanskaCKLR #online: Beyond Backprop: Online Alternating Minimization with Auxiliary Variables (AC, BC, SK, RL, MR, IR, PD, VG, BK, RT, DB0), pp. 1193–1202.
ICML-2019-ChoromanskiRCW #monte carlo #orthogonal: Unifying Orthogonal Monte Carlo Methods (KC, MR, WC, AW), pp. 1203–1212.
ICML-2019-ChuBG #functional #learning #probability: Probability Functional Descent: A Unifying Perspective on GANs, Variational Inference, and Reinforcement Learning (CC, JHB, PWG), pp. 1213–1222.
ICML-2019-ChuL #multi #named #summary: MeanSum: A Neural Model for Unsupervised Multi-Document Abstractive Summarization (EC, PJL), pp. 1223–1232.
ICML-2019-ChungL #detection: Weak Detection of Signal in the Spiked Wigner Model (HWC, JOL), pp. 1233–1241.
ICML-2019-CicaleseLM #clustering: New results on information theoretic clustering (FC, ESL, LM), pp. 1242–1251.
ICML-2019-CinelliKCPB #analysis #linear #modelling: Sensitivity Analysis of Linear Structural Causal Models (CC, DK, BC, JP, EB), pp. 1252–1261.
ICML-2019-ClarksonWW #reduction: Dimensionality Reduction for Tukey Regression (KLC, RW, DPW), pp. 1262–1271.
ICML-2019-ClemenconLB #on the #random: On Medians of (Randomized) Pairwise Means (SC, PL, PB), pp. 1272–1281.
ICML-2019-CobbeKHKS #learning: Quantifying Generalization in Reinforcement Learning (KC, OK, CH, TK, JS), pp. 1282–1289.
ICML-2019-CohenB #analysis #empirical #modelling #performance #sequence: Empirical Analysis of Beam Search Performance Degradation in Neural Sequence Models (EC, JCB), pp. 1290–1299.
ICML-2019-CohenKM #learning: Learning Linear-Quadratic Regulators Efficiently with only √T Regret (AC, TK, YM), pp. 1300–1309.
ICML-2019-CohenRK #random #robust: Certified Adversarial Robustness via Randomized Smoothing (JMC, ER, JZK), pp. 1310–1320.
ICML-2019-CohenWKW #network: Gauge Equivariant Convolutional Networks and the Icosahedral CNN (TC, MW, BK, MW), pp. 1321–1330.
ICML-2019-ColasOSFC #composition #learning #motivation #multi #named: CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning (CC, PYO, OS, PF, MC), pp. 1331–1340.
ICML-2019-CollobertHS: A fully differentiable beam search decoder (RC, AH, GS), pp. 1341–1350.
ICML-2019-CornishVBDD #dataset #scalability: Scalable Metropolis-Hastings for Exact Bayesian Inference with Large Datasets (RC, PV, ABC, GD, AD), pp. 1351–1360.
ICML-2019-Correa0B: Adjustment Criteria for Generalizing Experimental Findings (JDC, JT0, EB), pp. 1361–1369.
ICML-2019-CortesDGMY #feedback #graph #learning #online: Online Learning with Sleeping Experts and Feedback Graphs (CC, GD, CG, MM, SY), pp. 1370–1378.
ICML-2019-CortesDMZG #graph #learning: Active Learning with Disagreement Graphs (CC, GD, MM, NZ, CG), pp. 1379–1387.
ICML-2019-CotterGJLMNWZ #constraints #set: Shape Constraints for Set Functions (AC, MRG, HJ, EL, JM, TN, SW, TZ), pp. 1388–1396.
ICML-2019-CotterGJSSWWY #classification #constraints #metric: Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints (AC, MRG, HJ, NS, KS, SW, BEW, SY), pp. 1397–1405.
ICML-2019-CrankoMNOSW: Monge blunts Bayes: Hardness Results for Adversarial Training (ZC, AKM, RN, CSO, ZS, CJW), pp. 1406–1415.
ICML-2019-CrankoN #estimation: Boosted Density Estimation Remastered (ZC, RN), pp. 1416–1425.
ICML-2019-CrawfordKT #approximate: Submodular Cost Submodular Cover with an Approximate Oracle (VGC, AK, MTT), pp. 1426–1435.
ICML-2019-CreagerMJWSPZ #learning #representation: Flexibly Fair Representation Learning by Disentanglement (EC, DM, JHJ, MAW, KS, TP, RSZ), pp. 1436–1445.
ICML-2019-Cutkosky: Anytime Online-to-Batch, Optimism and Acceleration (AC), pp. 1446–1454.
ICML-2019-CutkoskyS #learning #online: Matrix-Free Preconditioning in Online Learning (AC, TS), pp. 1455–1464.
ICML-2019-CvitkovicK #learning #statistics: Minimal Achievable Sufficient Statistic Learning (MC, GK), pp. 1465–1474.
ICML-2019-CvitkovicSA #learning #source code: Open Vocabulary Learning on Source Code with a Graph-Structured Cache (MC, BS, AA), pp. 1475–1485.
ICML-2019-DadashiBTRS #learning: The Value Function Polytope in Reinforcement Learning (RD, MGB, AAT, NLR, DS), pp. 1486–1495.
ICML-2019-DaiYLJ #optimisation: Bayesian Optimization Meets Bayesian Optimal Stopping (ZD, HY, BKHL, PJ), pp. 1496–1506.
ICML-2019-Dann0WB #learning #policy #towards: Policy Certificates: Towards Accountable Reinforcement Learning (CD, LL0, WW, EB), pp. 1507–1516.
ICML-2019-DaoGERR #algorithm #learning #linear #performance #using: Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations (TD, AG, ME, AR, CR), pp. 1517–1527.
ICML-2019-DaoGRSSR #kernel: A Kernel Theory of Modern Data Augmentation (TD, AG, AR, VS, CDS, CR), pp. 1528–1537.
ICML-2019-DasGRBPRP #communication #multi #named: TarMAC: Targeted Multi-Agent Communication (AD, TG, JR, DB, DP, MR, JP), pp. 1538–1546.
ICML-2019-Dasgupta0PZ #black box #education: Teaching a black-box learner (SD, DH0, SP, XZ0), pp. 1547–1555.
ICML-2019-BiePC #network #probability: Stochastic Deep Networks (GdB, GP, MC), pp. 1556–1565.
ICML-2019-DeneviCGP #probability: Learning-to-Learn Stochastic Gradient Descent with Biased Regularization (GD, CC, RG, MP), pp. 1566–1575.
ICML-2019-DereliOG #algorithm #analysis #biology #kernel #learning #multi: A Multitask Multiple Kernel Learning Algorithm for Survival Analysis with Application to Cancer Biology (OD, CO, MG), pp. 1576–1585.
ICML-2019-DiaconuW #approach #learning: Learning to Convolve: A Generalized Weight-Tying Approach (ND, DEW), pp. 1586–1595.
ICML-2019-DiakonikolasKK0 #named #optimisation #probability #robust: Sever: A Robust Meta-Algorithm for Stochastic Optimization (ID, GK0, DK, JL0, JS, AS), pp. 1596–1606.
ICML-2019-DingDGHY #approximate #optimisation: Approximated Oracle Filter Pruning for Destructive CNN Width Optimization (XD, GD, YG, JH, CY), pp. 1607–1616.
ICML-2019-DingZDYRTV #component: Noisy Dual Principal Component Pursuit (TD, ZZ, TD, YY, DPR, MCT, RV), pp. 1617–1625.
ICML-2019-DoanMR #analysis #approximate #distributed #finite #learning #linear #multi: Finite-Time Analysis of Distributed TD(0) with Linear Function Approximation on Multi-Agent Reinforcement Learning (TTD, STM, JR), pp. 1626–1635.
ICML-2019-DoerrVTTD #learning: Trajectory-Based Off-Policy Deep Reinforcement Learning (AD, MV, MT, ST, CD), pp. 1636–1645.
ICML-2019-Dohmatob #robust #theorem: Generalized No Free Lunch Theorem for Adversarial Robustness (ED), pp. 1646–1654.
ICML-2019-DuH #linear #matter #network #optimisation: Width Provably Matters in Optimization for Deep Linear Neural Networks (SSD, WH), pp. 1655–1664.
ICML-2019-DuKJAD0 #performance: Provably efficient RL with Rich Observations via Latent State Decoding (SSD, AK, NJ, AA, MD, JL0), pp. 1665–1674.
ICML-2019-DuLL0Z #network: Gradient Descent Finds Global Minima of Deep Neural Networks (SSD, JDL, HL, LW0, XZ), pp. 1675–1685.
ICML-2019-DuL: Incorporating Grouping Information into Bayesian Decision Tree Ensembles (JD, ARL), pp. 1686–1695.
ICML-2019-DuN #learning: Task-Agnostic Dynamics Priors for Deep Reinforcement Learning (YD, KN), pp. 1696–1705.
ICML-2019-Duetting0NPR #learning: Optimal Auctions through Deep Learning (PD, ZF0, HN, DCP, SSR), pp. 1706–1715.
ICML-2019-DuklerLLM #generative #learning #modelling: Wasserstein of Wasserstein Loss for Learning Generative Models (YD, WL, ATL, GM), pp. 1716–1725.
ICML-2019-DunckerBBS #learning #modelling #probability: Learning interpretable continuous-time models of latent stochastic dynamical systems (LD, GB, JB, MS), pp. 1726–1734.
ICML-2019-DurkanN #energy: Autoregressive Energy Machines (CD, CN), pp. 1735–1744.
ICML-2019-DziedzicPKEF #network: Band-limited Training and Inference for Convolutional Neural Networks (AD, JP, SK, AJE, MJF), pp. 1745–1754.
ICML-2019-EdwardsSSI #policy: Imitating Latent Policies from Observation (ADE, HS, YS, CLIJ), pp. 1755–1763.
ICML-2019-EichnerKMST #probability: Semi-Cyclic Stochastic Gradient Descent (HE, TK, BM, NS, KT), pp. 1764–1773.
ICML-2019-ElfekiCRE #learning #named #process #using: GDPP: Learning Diverse Generations using Determinantal Point Processes (ME, CC, MR, ME), pp. 1774–1783.
ICML-2019-Elhamifar #algorithm #approximate: Sequential Facility Location: Approximate Submodularity and Greedy Algorithm (EE), pp. 1784–1793.
ICML-2019-EneV #convergence: Improved Convergence for l₁ and l₁ l∞ Regression via Iteratively Reweighted Least Squares (AE, AV), pp. 1794–1801.
ICML-2019-EngstromTTSM #robust: Exploring the Landscape of Spatial Robustness (LE, BT, DT, LS, AM), pp. 1802–1811.
ICML-2019-EstevesSLDM #3d #image: Cross-Domain 3D Equivariant Image Embeddings (CE, AS, ZL, KD, AM), pp. 1812–1822.
ICML-2019-EtmannLMS #on the #robust: On the Connection Between Adversarial Robustness and Saliency Map Interpretability (CE, SL, PM, CS), pp. 1823–1832.
ICML-2019-FahrbachMZ #adaptation #complexity #query: Non-monotone Submodular Maximization with Nearly Optimal Adaptivity and Query Complexity (MF, VSM, MZ), pp. 1833–1842.
ICML-2019-FanZ #multi: Multi-Frequency Vector Diffusion Maps (YF, ZZ), pp. 1843–1852.
ICML-2019-FarinaKBS #predict: Stable-Predictive Optimistic Counterfactual Regret Minimization (GF, CK, NB, TS), pp. 1853–1862.
ICML-2019-FarinaKS: Regret Circuits: Composability of Regret Minimizers (GF, CK, TS), pp. 1863–1872.
ICML-2019-FatemiSSK #learning: Dead-ends and Secure Exploration in Reinforcement Learning (MF, SS, HvS, SEK), pp. 1873–1881.
ICML-2019-Feige #invariant #learning #multi #representation: Invariant-Equivariant Representation Learning for Multi-Class Data (IF), pp. 1882–1891.
ICML-2019-FeldmanFH #multi #reuse #testing: The advantages of multiple classes for reducing overfitting from test set reuse (VF, RF, MH), pp. 1892–1900.
ICML-2019-FeraudAL #distributed #multi: Decentralized Exploration in Multi-Armed Bandits (RF, RA, RL), pp. 1901–1909.
ICML-2019-FercoqANC #optimisation: Almost surely constrained convex optimization (OF, AA, IN, VC), pp. 1910–1919.
ICML-2019-FinnRKL #online: Online Meta-Learning (CF, AR, SMK, SL), pp. 1920–1930.
ICML-2019-FischerBDGZV #logic #named #network #query: DL2: Training and Querying Neural Networks with Logic (MF, MB, DDC, TG, CZ, MTV), pp. 1931–1941.
ICML-2019-FoersterSHBDWBB #learning #multi: Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning (JNF, HFS, EH, NB, ID, SW, MB, MB), pp. 1942–1951.
ICML-2019-FongLH #multimodal #parametricity #scalability: Scalable Nonparametric Sampling from Multimodal Posteriors with the Posterior Bootstrap (EF, SL, CCH), pp. 1952–1962.
ICML-2019-FrancP #learning #nondeterminism #on the #predict: On discriminative learning of prediction uncertainty (VF, DP), pp. 1963–1971.
ICML-2019-FranceschiNPH #graph #learning #network: Learning Discrete Structures for Graph Neural Networks (LF, MN, MP, XH), pp. 1972–1982.
ICML-2019-FreirichSMT #evaluation #multi #policy: Distributional Multivariate Policy Evaluation and Exploration with the Bellman GAN (DF, TS, RM, AT), pp. 1983–1992.
ICML-2019-FrerixB #approximate #effectiveness #matrix #orthogonal: Approximating Orthogonal Matrices with Effective Givens Factorization (TF, JB), pp. 1993–2001.
ICML-2019-FrognerP #flexibility #performance: Fast and Flexible Inference of Joint Distributions from their Marginals (CF, TAP), pp. 2002–2011.
ICML-2019-FrosstPH #nearest neighbour: Analyzing and Improving Representations with the Soft Nearest Neighbor Loss (NF, NP, GEH), pp. 2012–2020.
ICML-2019-FuKSL #algorithm: Diagnosing Bottlenecks in Deep Q-learning Algorithms (JF, AK, MS, SL), pp. 2021–2030.
ICML-2019-FuLTL #black box #generative #metric #named #network #optimisation #speech: MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement (SWF, CFL, YT0, SDL), pp. 2031–2041.
ICML-2019-FujiiS #adaptation #approximate #policy: Beyond Adaptive Submodularity: Approximation Guarantees of Greedy Policy with Adaptive Submodularity Ratio (KF, SS), pp. 2042–2051.
ICML-2019-FujimotoMP #learning: Off-Policy Deep Reinforcement Learning without Exploration (SF, DM, DP), pp. 2052–2062.
ICML-2019-GamrianG #learning: Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation (SG, YG), pp. 2063–2072.
ICML-2019-GaneaGBS: Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities (OG, SG, GB, AS), pp. 2073–2082.
ICML-2019-GaoJ #graph: Graph U-Nets (HG, SJ), pp. 2083–2092.
ICML-2019-GaoJWWYZ #generative #learning: Deep Generative Learning via Variational Gradient Flow (YG, YJ, YW, YW0, CY, SZ), pp. 2093–2101.
ICML-2019-GaoL0O #theory and practice: Rate Distortion For Model Compression: From Theory To Practice (WG, YHL, CW0, SO), pp. 2102–2111.
ICML-2019-GaoPH: Demystifying Dropout (HG, JP, HH), pp. 2112–2121.
ICML-2019-GaoWH #data analysis #geometry #graph: Geometric Scattering for Graph Data Analysis (FG, GW, MJH), pp. 2122–2131.
ICML-2019-GaoZ #multi: Multi-Frequency Phase Synchronization (TG, ZZ), pp. 2132–2141.
ICML-2019-GazagnadouGS: Optimal Mini-Batch and Step Sizes for SAGA (NG, RMG, JS), pp. 2142–2150.
ICML-2019-GeifmanE #named #network: SelectiveNet: A Deep Neural Network with an Integrated Reject Option (YG, REY), pp. 2151–2159.
ICML-2019-GeistSP #formal method #markov #process: A Theory of Regularized Markov Decision Processes (MG, BS, OP), pp. 2160–2169.
ICML-2019-GeladaKBNB #learning #modelling #named #representation: DeepMDP: Learning Continuous Latent Space Models for Representation Learning (CG, SK, JB, ON, MGB), pp. 2170–2179.
ICML-2019-GengYKK #linear #modelling #visual notation: Partially Linear Additive Gaussian Graphical Models (SG, MY, MK, SK), pp. 2180–2190.
ICML-2019-GhadikolaeiGFS #big data #dataset #learning: Learning and Data Selection in Big Datasets (HSG, HGG, CF, MS), pp. 2191–2200.
ICML-2019-GhaffariLM #algorithm #clustering #network #parallel: Improved Parallel Algorithms for Density-Based Network Clustering (MG, SL, SM), pp. 2201–2210.
ICML-2019-GhaziPW #composition #learning #recursion #sketching: Recursive Sketches for Modular Deep Learning (BG, RP, JRW), pp. 2211–2220.
ICML-2019-GhorbaniJM #modelling #topic: An Instability in Variational Inference for Topic Models (BG, HJ, AM), pp. 2221–2231.
ICML-2019-GhorbaniKX #optimisation: An Investigation into Neural Net Optimization via Hessian Eigenvalue Density (BG, SK, YX), pp. 2232–2241.
ICML-2019-GhorbaniZ #machine learning: Data Shapley: Equitable Valuation of Data for Machine Learning (AG, JYZ), pp. 2242–2251.
ICML-2019-GilboaB0 #learning #performance #taxonomy: Efficient Dictionary Learning with Gradient Descent (DG, SB, JW0), pp. 2252–2259.
ICML-2019-GillenwaterKMV #performance #process: A Tree-Based Method for Fast Repeated Sampling of Determinantal Point Processes (JG, AK, ZM, SV), pp. 2260–2268.
ICML-2019-GillickREEB #learning #sequence: Learning to Groove with Inverse Sequence Transformations (JG, AR, JHE, DE, DB), pp. 2269–2279.
ICML-2019-GilmerFCC #fault: Adversarial Examples Are a Natural Consequence of Test Error in Noise (JG, NF, NC, EDC), pp. 2280–2289.
ICML-2019-GimenezZ #statistics: Discovering Conditionally Salient Features with Statistical Guarantees (JRG, JYZ), pp. 2290–2298.
ICML-2019-GoldfeldBGMNKP #data flow #network: Estimating Information Flow in Deep Neural Networks (ZG, EvdB, KHG, IM, NN, BK, YP), pp. 2299–2308.
ICML-2019-GolinskiWR #integration #monte carlo: Amortized Monte Carlo Integration (AG, FW, TR), pp. 2309–2318.
ICML-2019-GollapudiP #algorithm #online: Online Algorithms for Rent-Or-Buy with Expert Advice (SG, DP), pp. 2319–2327.
ICML-2019-GolovnevPS #learning: The information-theoretic value of unlabeled data in semi-supervised learning (AG, DP, BS), pp. 2328–2336.
ICML-2019-GongHLQWL #performance: Efficient Training of BERT by Progressively Stacking (LG, DH, ZL, TQ, LW0, TYL), pp. 2337–2346.
ICML-2019-Gong0L #optimisation: Quantile Stein Variational Gradient Descent for Batch Bayesian Optimization (CG, JP0, QL0), pp. 2347–2356.
ICML-2019-GordalizaBGL #using: Obtaining Fairness using Optimal Transport Theory (PG, EdB, FG, JML), pp. 2357–2365.
ICML-2019-GottesmanLSBD #evaluation #modelling #parametricity: Combining parametric and nonparametric models for off-policy evaluation (OG, YL0, SS, EB, FDV), pp. 2366–2375.
ICML-2019-GoyalWEBPL #visual notation: Counterfactual Visual Explanations (YG, ZW, JE, DB, DP, SL), pp. 2376–2384.
ICML-2019-GrantBGLVC #adaptation: Adaptive Sensor Placement for Continuous Spaces (JAG, AB, RRG, DSL, SV, EMdC), pp. 2385–2393.
ICML-2019-Greaves-Tunnell #memory management #music #statistics: A Statistical Investigation of Long Memory in Language and Music (AGT, ZH), pp. 2394–2403.
ICML-2019-GreenbergNM #automation: Automatic Posterior Transformation for Likelihood-Free Inference (DSG, MN, JHM), pp. 2404–2414.
ICML-2019-GreenfeldGBYK #learning #multi: Learning to Optimize Multigrid PDE Solvers (DG, MG, RB, IY, RK), pp. 2415–2423.
ICML-2019-GreffKKWBZMBL #learning #multi #representation: Multi-Object Representation Learning with Iterative Variational Inference (KG, RLK, RK, NW, CB, DZ, LM, MB, AL), pp. 2424–2433.
ICML-2019-GroverZE #generative #graph #modelling #named: Graphite: Iterative Generative Modeling of Graphs (AG, AZ, SE), pp. 2434–2444.
ICML-2019-GuY #algorithm #modelling #multi #performance #ranking: Fast Algorithm for Generalized Multinomial Models with Ranking Data (JG, GY), pp. 2445–2453.
ICML-2019-GuanWZCH0 #comprehension #modelling #towards: Towards a Deep and Unified Understanding of Deep Neural Models in NLP (CG, XW, QZ, RC, DH, XX0), pp. 2454–2463.
ICML-2019-GuezMGKRWRSOEWS: An Investigation of Model-Free Planning (AG, MM, KG, RK, SR, TW, DR, AS, LO, TE, GW, DS, TPL), pp. 2464–2473.
ICML-2019-GultchinPBSK #word: Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops (LG, GP, NB, NS, AK), pp. 2474–2483.
ICML-2019-GuoGYWW #black box: Simple Black-box Adversarial Attacks (CG, JRG, YY, AGW, KQW), pp. 2484–2493.
ICML-2019-0002LA #multi #network: Exploring interpretable LSTM neural networks over multi-variable data (TG0, TL, NAF), pp. 2494–2504.
ICML-2019-GuoSH #dependence #graph #learning #relational: Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs (LG, ZS, WH0), pp. 2505–2514.
ICML-2019-GuralM #classification #embedded: Memory-Optimal Direct Convolutions for Maximizing Classification Accuracy in Embedded Applications (AG, BM), pp. 2515–2524.
ICML-2019-HaberLTR #network: IMEXnet A Forward Stable Deep Neural Network (EH, KL, ET, LR), pp. 2525–2534.
ICML-2019-HacohenW #education #learning #network #on the #power of: On The Power of Curriculum Learning in Training Deep Networks (GH, DW), pp. 2535–2544.
ICML-2019-HaddadpourKMC #communication #distributed #optimisation: Trading Redundancy for Communication: Speeding up Distributed SGD for Non-convex Optimization (FH, MMK, MM, VRC), pp. 2545–2554.
ICML-2019-HafnerLFVHLD #learning: Learning Latent Dynamics for Planning from Pixels (DH, TPL, IF, RV, DH, HL, JD), pp. 2555–2565.
ICML-2019-HalperinEH: Neural Separation of Observed and Unobserved Distributions (TH, AE, YH), pp. 2566–2575.
ICML-2019-HanSDXWSLZ #game studies #learning #multi #video: Grid-Wise Control for Multi-Agent Reinforcement Learning in Video Game AI (LH, PS, YD, JX, QW, XS, HL, TZ), pp. 2576–2585.
ICML-2019-HanS #learning: Dimension-Wise Importance Sampling Weight Clipping for Sample-Efficient Reinforcement Learning (SH, YS), pp. 2586–2595.
ICML-2019-HaninR #complexity #linear #network: Complexity of Linear Regions in Deep Networks (BH, DR), pp. 2596–2604.
ICML-2019-HannaNS #behaviour #evaluation #policy: Importance Sampling Policy Evaluation with an Estimated Behavior Policy (JH, SN, PS), pp. 2605–2613.
ICML-2019-HaoO #estimation: Doubly-Competitive Distribution Estimation (YH, AO), pp. 2614–2623.
ICML-2019-HaochenS #finite #random: Random Shuffling Beats SGD after Finite Epochs (JH, SS), pp. 2624–2633.
ICML-2019-HarshawFWK #algorithm #performance: Submodular Maximization beyond Non-negativity: Guarantees, Fast Algorithms, and Applications (CH, MF, JW, AK), pp. 2634–2643.
ICML-2019-HarutyunyanVHNP: Per-Decision Option Discounting (AH, PV, PH, AN, DP), pp. 2644–2652.
ICML-2019-HashemiGVT #information management #modelling #polynomial: Submodular Observation Selection and Information Gathering for Quadratic Models (AH, MG, HV, UT), pp. 2653–2662.
ICML-2019-HavivRB #comprehension #memory management #network: Understanding and Controlling Memory in Recurrent Neural Networks (DH, AR, OB), pp. 2663–2671.
ICML-2019-HayouDR #network #on the: On the Impact of the Activation function on Deep Neural Networks Training (SH, AD, JR), pp. 2672–2680.
ICML-2019-HazanKSS #performance: Provably Efficient Maximum Entropy Exploration (EH, SMK, KS, AVS), pp. 2681–2691.
ICML-2019-HeidariNG #algorithm #learning #on the #policy #social: On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness and Feature Segregation through Social Learning (HH, VN, KPG), pp. 2692–2701.
ICML-2019-HendrickxOS #graph #learning: Graph Resistance and Learning from Pairwise Comparisons (JMH, AO, VS), pp. 2702–2711.
ICML-2019-HendrycksLM #nondeterminism #robust #using: Using Pre-Training Can Improve Model Robustness and Uncertainty (DH, KL, MM), pp. 2712–2721.
ICML-2019-HoCSDA #architecture #design #generative #modelling: Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design (JH, XC0, AS, YD, PA), pp. 2722–2730.
ICML-2019-HoLCSA #learning #performance #policy: Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules (DH, EL, XC0, IS, PA), pp. 2731–2741.
ICML-2019-HoangHLK #black box #multi: Collective Model Fusion for Multiple Black-Box Experts (QMH, TNH, BKHL, CK), pp. 2742–2750.
ICML-2019-HoferKND #learning #persistent #representation: Connectivity-Optimized Representation Learning via Persistent Homology (CDH, RK, MN, MD), pp. 2751–2760.
ICML-2019-HollandI #robust #using: Better generalization with less data using robust gradient descent (MJH, KI), pp. 2761–2770.
ICML-2019-HoogeboomBW #generative #normalisation: Emerging Convolutions for Generative Normalizing Flows (EH, RvdB, MW), pp. 2771–2780.
ICML-2019-HorvathR #optimisation: Nonconvex Variance Reduced Optimization with Arbitrary Sampling (SH, PR), pp. 2781–2789.
ICML-2019-HoulsbyGJMLGAG #learning: Parameter-Efficient Transfer Learning for NLP (NH, AG, SJ, BM, QdL, AG, MA, SG), pp. 2790–2799.
ICML-2019-HsiehLBK #linear: Stay With Me: Lifetime Maximization Through Heteroscedastic Linear Bandits With Reneging (PCH, XL0, AB, PRK), pp. 2800–2809.
ICML-2019-HsiehLC #generative #nash #network: Finding Mixed Nash Equilibria of Generative Adversarial Networks (YPH, CL, VC), pp. 2810–2819.
ICML-2019-HsiehNS #classification: Classification from Positive, Unlabeled and Biased Negative Data (YGH, GN, MS), pp. 2820–2829.
ICML-2019-HsuR #kernel: Bayesian Deconditional Kernel Mean Embeddings (KH, FR), pp. 2830–2838.
ICML-2019-HuangCH #multi #optimisation #performance #probability: Faster Stochastic Alternating Direction Method of Multipliers for Nonconvex Optimization (FH, SC, HH), pp. 2839–2848.
ICML-2019-HuangDGZ #learning: Unsupervised Deep Learning by Neighbourhood Discovery (JH, QD0, SG, XZ), pp. 2849–2858.
ICML-2019-Huang0 #algorithm #community #correlation #detection: Detecting Overlapping and Correlated Communities without Pure Nodes: Identifiability and Algorithm (KH, XF0), pp. 2859–2868.
ICML-2019-HuangSDLC: Hierarchical Importance Weighted Autoencoders (CWH, KS, ED, AL, ACC), pp. 2869–2878.
ICML-2019-HuangV #classification: Stable and Fair Classification (LH, NKV), pp. 2879–2890.
ICML-2019-HuangZTMSGS #adaptation: Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment (CH, SZ, WT, MÁB0, SYS, CG, JMS), pp. 2891–2900.
ICML-2019-Huang0GG #modelling: Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models (BH, KZ0, MG, CG), pp. 2901–2910.
ICML-2019-HuntBLH #policy #using: Composing Entropic Policies using Divergence Correction (JJH, AB, TPL, NH), pp. 2911–2920.
ICML-2019-HwangJY #classification #generative #named: HexaGAN: Generative Adversarial Nets for Real World Classification (UH, DJ, SY), pp. 2921–2930.
ICML-2019-IalongoWHR #approximate #modelling #process: Overcoming Mean-Field Approximations in Recurrent Gaussian Process Models (ADI, MvdW, JH, CER), pp. 2931–2940.
ICML-2019-InnesL #learning #problem: Learning Structured Decision Problems with Unawareness (CI, AL), pp. 2941–2950.
ICML-2019-IpsenH #exclamation: Phase transition in PCA with missing data: Reduced signal-to-noise ratio, not sample size! (NBI, LKH), pp. 2951–2960.
ICML-2019-IqbalS #learning #multi: Actor-Attention-Critic for Multi-Agent Reinforcement Learning (SI, FS), pp. 2961–2970.
ICML-2019-IshidaNMS #learning #modelling: Complementary-Label Learning for Arbitrary Losses and Models (TI, GN, AKM, MS), pp. 2971–2980.
ICML-2019-JaberZB #equivalence #identification #markov: Causal Identification under Markov Equivalence: Completeness Results (AJ, JZ, EB), pp. 2981–2989.
ICML-2019-JacqGPP #learning: Learning from a Learner (AJ, MG, AP, OP), pp. 2990–2999.
ICML-2019-JagielskiKMORSU #learning: Differentially Private Fair Learning (MJ, MJK, JM, AO, AR0, SSM, JU), pp. 3000–3008.
ICML-2019-JainiSY #polynomial: Sum-of-Squares Polynomial Flow (PJ, KAS, YY), pp. 3009–3018.
ICML-2019-JangJ #clustering #performance #scalability #towards: DBSCAN++: Towards fast and scalable density clustering (JJ, HJ), pp. 3019–3029.
ICML-2019-JangLHS #learning #what: Learning What and Where to Transfer (YJ, HL, SJH, JS), pp. 3030–3039.
ICML-2019-JaquesLHGOSLF #learning #motivation #multi #social: Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning (NJ, AL, EH, ÇG, PAO, DS, JZL, NdF), pp. 3040–3049.
ICML-2019-JayRGST #internet #learning: A Deep Reinforcement Learning Perspective on Internet Congestion Control (NJ, NHR, BG, MS, AT), pp. 3050–3059.
ICML-2019-JeongKKN #graph #modelling #music #network #performance: Graph Neural Network for Music Score Data and Modeling Expressive Piano Performance (DJ, TK, YK, JN), pp. 3060–3070.
ICML-2019-JeongLK #network: Ladder Capsule Network (TJ, YL, HK), pp. 3071–3079.
ICML-2019-JeongS: Training CNNs with Selective Allocation of Channels (JJ, JS), pp. 3080–3090.
ICML-2019-JeongS19a #learning: Learning Discrete and Continuous Factors of Data via Alternating Disentanglement (YJ, HOS), pp. 3091–3099.
ICML-2019-JiWZL #algorithm #analysis #optimisation: Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization (KJ, ZW, YZ, YL), pp. 3100–3109.
ICML-2019-JiangL #learning #logic: Neural Logic Reinforcement Learning (ZJ, SL), pp. 3110–3119.
ICML-2019-JinnaiAHLK: Finding Options that Minimize Planning Time (YJ, DA, DEH, MLL, GDK), pp. 3120–3129.
ICML-2019-JinnaiPAK: Discovering Options for Exploration by Minimizing Cover Time (YJ, JWP, DA, GDK), pp. 3130–3139.
ICML-2019-JitkrittumSGRHS #kernel: Kernel Mean Matching for Content Addressability of GANs (WJ, PS, MWG, AR, JH, BS), pp. 3140–3151.
ICML-2019-JohnHS #difference #equation #named #off the shelf: GOODE: A Gaussian Off-The-Shelf Ordinary Differential Equation Solver (DJ, VH, MS), pp. 3152–3162.
ICML-2019-JunWWN #rank: Bilinear Bandits with Low-rank Structure (KSJ, RW, SW, RDN), pp. 3163–3172.
ICML-2019-KahngLNPP #statistics: Statistical Foundations of Virtual Democracy (AK, MKL, RN, ADP, CAP), pp. 3173–3182.
ICML-2019-Kajino #graph grammar #optimisation: Molecular Hypergraph Grammar with Its Application to Molecular Optimization (HK), pp. 3183–3191.
ICML-2019-KalimerisKS #modelling #robust: Robust Influence Maximization for Hyperparametric Models (DK, GK, YS), pp. 3192–3200.
ICML-2019-Kallus: Classifying Treatment Responders Under Causal Effect Monotonicity (NK), pp. 3201–3210.
ICML-2019-KalyanALB #modelling #sequence #set: Trainable Decoding of Sets of Sequences for Neural Sequence Models (AK, PA, SL, DB), pp. 3211–3221.
ICML-2019-KandasamyNZKSP #adaptation #design: Myopic Posterior Sampling for Adaptive Goal Oriented Design of Experiments (KK, WN, RZ, AK, JS, BP), pp. 3222–3232.
ICML-2019-KaplanMMS #concept #geometry #learning: Differentially Private Learning of Geometric Concepts (HK, YM, YM, US), pp. 3233–3241.
ICML-2019-KaplanisSC #learning #policy: Policy Consolidation for Continual Reinforcement Learning (CK, MS, CC), pp. 3242–3251.
ICML-2019-KarimireddyRSJ #fault #feedback: Error Feedback Fixes SignSGD and other Gradient Compression Schemes (SPK, QR, SUS, MJ), pp. 3252–3261.
ICML-2019-KasaiJM #adaptation #algorithm #matrix #probability: Riemannian adaptive stochastic gradient algorithms on matrix manifolds (HK, PJ, BM), pp. 3262–3271.
ICML-2019-KasparOMKM #image: Neural Inverse Knitting: From Images to Manufacturing Instructions (AK, THO, LM, PK, WM), pp. 3272–3281.
ICML-2019-KatharopoulosF #image #modelling: Processing Megapixel Images with Deep Attention-Sampling Models (AK, FF), pp. 3282–3291.
ICML-2019-KatiyarHC #estimation #modelling #robust #visual notation: Robust Estimation of Tree Structured Gaussian Graphical Models (AK, JH, CC), pp. 3292–3300.
ICML-2019-KayaHD #comprehension #network: Shallow-Deep Networks: Understanding and Mitigating Network Overthinking (YK, SH, TD), pp. 3301–3310.
ICML-2019-0001MZLK #adaptation #approximate #complexity #memory management #streaming: Submodular Streaming in All Its Glory: Tight Approximation, Minimum Memory and Low Adaptive Complexity (EK0, MM, MZ, SL, AK), pp. 3311–3320.
ICML-2019-KempkaKW #adaptation #algorithm #invariant #learning #linear #modelling #online: Adaptive Scale-Invariant Online Algorithms for Learning Linear Models (MK, WK, MKW), pp. 3321–3330.
ICML-2019-KenterWCCV #named #network #speech #synthesis: CHiVE: Varying Prosody in Speech Synthesis with a Linguistically Driven Dynamic Hierarchical Conditional Variational Network (TK, VW, CaC, RC, JV), pp. 3331–3340.
ICML-2019-KhadkaMNDTMLT #collaboration #learning: Collaborative Evolutionary Reinforcement Learning (SK, SM, TN, ZD, ET, SM, YL, KT), pp. 3341–3350.
ICML-2019-KhasanovaF #geometry #image #representation: Geometry Aware Convolutional Filters for Omnidirectional Images Representation (RK, PF), pp. 3351–3359.
ICML-2019-KimKJLS #named: EMI: Exploration with Mutual Information (HK, JK, YJ, SL, HOS), pp. 3360–3369.
ICML-2019-KimLSKY #generative: FloWaveNet : A Generative Flow for Raw Audio (SK, SgL, JS, JK, SY), pp. 3370–3378.
ICML-2019-KimNKKK #named: Curiosity-Bottleneck: Exploration By Distilling Task-Specific Novelty (YK, WN, HK, JHK, GK), pp. 3379–3388.
ICML-2019-KimP #algorithm #multi: Contextual Multi-armed Bandit Algorithm for Semiparametric Reward Model (GSK, MCP), pp. 3389–3397.
ICML-2019-KimSRW #adaptation #convergence #kernel: Uniform Convergence Rate of the Kernel Density Estimator Adaptive to Intrinsic Volume Dimension (JK, JS, AR, LAW), pp. 3398–3407.
ICML-2019-KingmaAH #named #recursion: Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variables (FHK, PA, JH), pp. 3408–3417.
ICML-2019-KipfLDZSGKB #composition #execution #learning #named: CompILE: Compositional Imitation Learning and Execution (TK, YL, HD, VFZ, ASG, EG, PK, PWB), pp. 3418–3428.
ICML-2019-KirschnerMHI0 #adaptation #optimisation: Adaptive and Safe Bayesian Optimization in High Dimensions via One-Dimensional Subspaces (JK, MM, NH, RI, AK0), pp. 3429–3438.
ICML-2019-KleimanP #machine learning #metric #modelling #multi #named #performance: AUCμ: A Performance Metric for Multi-Class Machine Learning Models (RK, DP), pp. 3439–3447.
ICML-2019-KleindessnerAM #clustering #summary: Fair k-Center Clustering for Data Summarization (MK, PA, JM), pp. 3448–3457.
ICML-2019-KleindessnerSAM #clustering #constraints: Guarantees for Spectral Clustering with Fairness Constraints (MK, SS, PA, JM), pp. 3458–3467.
ICML-2019-KoLWDWL #named #network #robust: POPQORN: Quantifying Robustness of Recurrent Neural Networks (CYK, ZL, LW, LD, NW, DL), pp. 3468–3477.
ICML-2019-KoloskovaSJ #algorithm #communication #distributed #optimisation #probability: Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication (AK, SUS, MJ), pp. 3478–3487.
ICML-2019-KonstantinovL #learning #robust: Robust Learning from Untrusted Sources (NK, CL), pp. 3488–3498.
ICML-2019-KoolHW #probability #sequence: Stochastic Beams and Where To Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement (WK, HvH, MW), pp. 3499–3508.
ICML-2019-KoratanaKBZ #named #representation: LIT: Learned Intermediate Representation Training for Model Compression (AK, DK, PB, MZ), pp. 3509–3518.
ICML-2019-Kornblith0LH #network #revisited #similarity: Similarity of Neural Network Representations Revisited (SK, MN0, HL, GEH), pp. 3519–3529.
ICML-2019-KroshninTDDGU #approximate #complexity #on the: On the Complexity of Approximating Wasserstein Barycenters (AK, NT, DD, PED, AG, CAU), pp. 3530–3540.
ICML-2019-KulunchakovM #optimisation #probability #sequence: Estimate Sequences for Variance-Reduced Stochastic Composite Optimization (AK, JM), pp. 3541–3550.
ICML-2019-0001PRW #algorithm #matrix #performance: Faster Algorithms for Binary Matrix Factorization (RK0, RP, AR, DPW), pp. 3551–3559.
ICML-2019-KuninBGS #linear: Loss Landscapes of Regularized Linear Autoencoders (DK, JMB, AG, CS), pp. 3560–3569.
ICML-2019-KuoLZ0 #geometry #symmetry: Geometry and Symmetry in Short-and-Sparse Deconvolution (HWK, YL, YZ, JW0), pp. 3570–3580.
ICML-2019-KurachLZMG #normalisation #scalability: A Large-Scale Study on Regularization and Normalization in GANs (KK, ML, XZ, MM, SG), pp. 3581–3590.
ICML-2019-Kusner0LS: Making Decisions that Reduce Discriminatory Impacts (MJK, CR0, JRL, RS), pp. 3591–3600.
ICML-2019-KvetonSVWLG #multi: Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits (BK, CS, SV, ZW, TL, MG), pp. 3601–3610.
ICML-2019-Labatie #network: Characterizing Well-Behaved vs. Pathological Deep Neural Networks (AL), pp. 3611–3621.
ICML-2019-LambBGSMBM #modelling #network: State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations (AL, JB, AG, SS, IM, YB, MM), pp. 3622–3631.
ICML-2019-Lamprier: A Recurrent Neural Cascade-based Model for Continuous-Time Diffusion (SL), pp. 3632–3641.
ICML-2019-WonXL #learning: Projection onto Minkowski Sums with Application to Constrained Learning (JHW, JX, KL), pp. 3642–3651.
ICML-2019-LarocheTC #policy: Safe Policy Improvement with Baseline Bootstrapping (RL, PT, RTdC), pp. 3652–3661.
ICML-2019-LattanziS #algorithm: A Better k-means++ Algorithm via Local Search (SL, CS), pp. 3662–3671.
ICML-2019-LawLSZ #distance #learning: Lorentzian Distance Learning for Hyperbolic Representations (MTL, RL, JS, RSZ), pp. 3672–3681.
ICML-2019-LawrenceEC #dependence #learning #multi #named #parametricity: DP-GP-LVM: A Bayesian Non-Parametric Model for Learning Multivariate Dependency Structures (ARL, CHE, NDFC), pp. 3682–3691.
ICML-2019-X #bound #named #policy #predict #using: POLITEX: Regret Bounds for Policy Iteration using Expert Prediction, pp. 3692–3702.
ICML-2019-0002VY #constraints #learning #policy: Batch Policy Learning under Constraints (HML0, CV, YY), pp. 3703–3712.
ICML-2019-0002H #learning: Target-Based Temporal-Difference Learning (DL0, NH), pp. 3713–3722.
ICML-2019-LeeJAJ #approach #functional #game studies: Functional Transparency for Structured Data: a Game-Theoretic Approach (GHL, WJ, DAM, TSJ), pp. 3723–3733.
ICML-2019-LeeLK #graph #self: Self-Attention Graph Pooling (JL, IL, JK), pp. 3734–3743.
ICML-2019-LeeLKKCT #framework #invariant #network #set: Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks (JL, YL, JK, ARK, SC, YWT), pp. 3744–3753.
ICML-2019-LeeW #algorithm #first-order #performance #problem: First-Order Algorithms Converge Faster than $O(1/k)$ on Convex Problems (CPL, SW), pp. 3754–3762.
ICML-2019-LeeYLLLS #classification #generative #robust: Robust Inference via Generative Classifiers for Handling Noisy Labels (KL, SY, KL, HL, BL, JS), pp. 3763–3772.
ICML-2019-LeiHKT #nearest neighbour #sublinear: Sublinear Time Nearest Neighbor Search over Generalized Weighted Space (YL, QH, MSK, AKHT), pp. 3773–3781.
ICML-2019-LerasleSML #estimation: MONK Outlier-Robust Mean Embedding Estimation by Median-of-Means (ML, ZS, TM, GL), pp. 3782–3793.
ICML-2019-CasadoM #constraints #network #orthogonal: Cheap Orthogonal Constraints in Neural Networks: A Simple Parametrization of the Orthogonal and Unitary Group (MLC, DMR), pp. 3794–3803.
ICML-2019-LiBS #classification #generative #question #robust: Are Generative Classifiers More Robust to Adversarial Attacks? (YL, JB, YS), pp. 3804–3814.
ICML-2019-LiCW #algorithm #classification #kernel #linear #quantum #sublinear: Sublinear quantum algorithms for training linear and kernel-based classifiers (TL, SC, XW), pp. 3815–3824.
ICML-2019-LiDMMHH #learning #named #network: LGM-Net: Learning to Generate Matching Networks for Few-Shot Learning (HYL, WD, XM, CM, FH, BGH), pp. 3825–3834.
ICML-2019-LiGDVK #graph #learning #network #similarity: Graph Matching Networks for Learning the Similarity of Graph Structured Objects (YL, CG, TD, OV, PK), pp. 3835–3845.
ICML-2019-LiKBS: Area Attention (YL0, LK, SB, SS), pp. 3846–3855.
ICML-2019-LiLS #learning #online #rank: Online Learning to Rank with Features (SL, TL, CS), pp. 3856–3865.
ICML-2019-LiLWZG #black box #learning #named #network: NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks (YL, LL, LW, TZ, BG), pp. 3866–3876.
ICML-2019-LiMC #visual notation: Bayesian Joint Spike-and-Slab Graphical Lasso (ZRL, THM, SJC), pp. 3877–3885.
ICML-2019-LiRC #correlation #crowdsourcing: Exploiting Worker Correlation for Label Aggregation in Crowdsourcing (YL0, BIPR, TC), pp. 3886–3895.
ICML-2019-LiSK #learning #physics: Adversarial camera stickers: A physical camera-based attack on deep learning systems (JL0, FRS, JZK), pp. 3896–3904.
ICML-2019-LiTOS #analysis #fourier #random #towards: Towards a Unified Analysis of Random Fourier Features (ZL, JFT, DO, DS), pp. 3905–3914.
ICML-2019-LiYZH #network: Feature-Critic Networks for Heterogeneous Domain Generalization (YL, YY, WZ, TMH), pp. 3915–3924.
ICML-2019-LiZWSX #framework #learning: Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting (XL, YZ, TW, RS, CX), pp. 3925–3934.
ICML-2019-LiZT #higher-order: Alternating Minimizations Converge to Second-Order Optimal Solutions (QL, ZZ, GT), pp. 3935–3943.
ICML-2019-LiakopoulosDPSM #constraints #online #optimisation: Cautious Regret Minimization: Online Optimization with Long-Term Budget Constraints (NL, AD, GSP, TS, PM), pp. 3944–3952.
ICML-2019-LichtenbergS: Regularization in directable environments with application to Tetris (JML, ÖS), pp. 3953–3962.
ICML-2019-LikhosherstovMC #modelling: Inference and Sampling of $K_33$-free Ising Models (VL, YM, MC), pp. 3963–3972.
ICML-2019-LimA #kernel #learning #markov #process #robust: Kernel-Based Reinforcement Learning in Robust Markov Decision Processes (SHL, AA), pp. 3973–3981.
ICML-2019-LinHJ #algorithm #analysis #on the #performance: On Efficient Optimal Transport: An Analysis of Greedy and Accelerated Mirror Descent Algorithms (TL, NH, MIJ), pp. 3982–3991.
ICML-2019-LinKS #approximate #performance: Fast and Simple Natural-Gradient Variational Inference with Mixture of Exponential-family Approximations (WL, MEK, MWS), pp. 3992–4002.
ICML-2019-LiuFY: Acceleration of SVRG and Katyusha X by Inexact Preconditioning (YL0, FF, WY), pp. 4003–4012.
ICML-2019-LiuLWJ #adaptation #approach #classification: Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers (HL, ML, JW0, MIJ), pp. 4013–4022.
ICML-2019-LiuRTJM #probability: Rao-Blackwellized Stochastic Gradients for Discrete Distributions (RL, JR, NT, MIJ, JDM), pp. 4023–4031.
ICML-2019-LiuS #learning #multi: Sparse Extreme Multi-label Learning with Oracle Property (WL, XS0), pp. 4032–4041.
ICML-2019-LiuS19a #probability: Data Poisoning Attacks on Stochastic Bandits (FL0, NBS), pp. 4042–4050.
ICML-2019-LiuSH #learning: The Implicit Fairness Criterion of Unconstrained Learning (LTL, MS, MH), pp. 4051–4060.
ICML-2019-LiuSX #learning #performance: Taming MAML: Efficient unbiased meta-reinforcement learning (HL, RS, CX), pp. 4061–4071.
ICML-2019-LiuTC #bound #on the: On Certifying Non-Uniform Bounds against Adversarial Attacks (CL, RT, VC), pp. 4072–4081.
ICML-2019-LiuZCZ0 #comprehension: Understanding and Accelerating Particle-Based Variational Inference (CL0, JZ, PC, RZ, JZ0), pp. 4082–4092.
ICML-2019-LiuZ0 #comprehension: Understanding MCMC Dynamics as Flows on the Wasserstein Space (CL0, JZ, JZ0), pp. 4093–4103.
ICML-2019-LiutkusSMDS #generative #modelling #parametricity: Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions (AL, US, SM, AD, FRS), pp. 4104–4113.
ICML-2019-LocatelloBLRGSB #learning: Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations (FL, SB, ML, GR, SG, BS, OB), pp. 4114–4124.
ICML-2019-LondonS: Bayesian Counterfactual Risk Minimization (BL, TS), pp. 4125–4133.
ICML-2019-LuHW #convergence #higher-order #named #optimisation: PA-GD: On the Convergence of Perturbed Alternating Gradient Descent to Second-Order Stationary Points for Structured Nonconvex Optimization (SL, MH, ZW), pp. 4134–4143.
ICML-2019-LuMT0: Neurally-Guided Structure Inference (SL, JM, JBT, JW0), pp. 4144–4153.
ICML-2019-LuWHZ #algorithm: Optimal Algorithms for Lipschitz Bandits with Heavy-tailed Rewards (SL, GW, YH, LZ0), pp. 4154–4163.
ICML-2019-LuYFZ0 #generative #modelling #named: CoT: Cooperative Training for Generative Modeling of Discrete Data (SL, LY, SF, YZ, WZ0), pp. 4164–4172.
ICML-2019-LucibelloSL #approximate #estimation #overview: Generalized Approximate Survey Propagation for High-Dimensional Estimation (CL, LS, YML), pp. 4173–4182.
ICML-2019-LucicTRZBG #generative #image: High-Fidelity Image Generation With Fewer Labels (ML, MT, MR, XZ, OB, SG), pp. 4183–4192.
ICML-2019-LuiseSPC #predict #rank: Leveraging Low-Rank Relations Between Surrogate Tasks in Structured Prediction (GL, DS, MP, CC), pp. 4193–4202.
ICML-2019-PingPSZRW #learning #normalisation #representation: Differentiable Dynamic Normalization for Learning Deep Representation (LP, ZP, WS, RZ, JR, LW), pp. 4203–4211.
ICML-2019-Ma0KW0 #graph #network: Disentangled Graph Convolutional Networks (JM, PC0, KK, XW0, WZ0), pp. 4212–4221.
ICML-2019-MaLH #process: Variational Implicit Processes (CM, YL, JMHL), pp. 4222–4233.
ICML-2019-MaTPHNZ #named #performance: EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE (CM, ST, KP, JMHL, SN, CZ), pp. 4234–4243.
ICML-2019-MagnussonAJV #scalability: Bayesian leave-one-out cross-validation for large data (MM, MRA, JJ, AV), pp. 4244–4253.
ICML-2019-MahabadiIGR #algorithm #composition: Composable Core-sets for Determinant Maximization: A Simple Near-Optimal Algorithm (SM, PI, SOG, AR), pp. 4254–4263.
ICML-2019-Maheswaranathan #random: Guided evolutionary strategies: augmenting random search with surrogate gradients (NM, LM, GT, DC, JSD), pp. 4264–4273.
ICML-2019-MahloujifarMM #learning #multi: Data Poisoning Attacks in Multi-Party Learning (SM, MM, AM), pp. 4274–4283.
ICML-2019-MahoneyM #modelling #network: Traditional and Heavy Tailed Self Regularization in Neural Network Models (MWM, CM), pp. 4284–4293.
ICML-2019-MaiJ: Curvature-Exploiting Acceleration of Elastic Net Computations (VVM, MJ0), pp. 4294–4303.
ICML-2019-MakkuvaVKO #algorithm #consistency #performance: Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient Algorithms (AVM, PV, SK, SO), pp. 4304–4313.
ICML-2019-MalikKSNSE #learning #modelling: Calibrated Model-Based Deep Reinforcement Learning (AM, VK, JS, DN, HS, SE), pp. 4314–4323.
ICML-2019-MannGGHJLS #learning #recommendation: Learning from Delayed Outcomes via Proxies with Applications to Recommender Systems (TAM, SG, AG, HH, RJ, BL, PS), pp. 4324–4332.
ICML-2019-MannelliKUZ #algorithm #modelling: Passed & Spurious: Descent Algorithms and Local Minima in Spiked Matrix-Tensor Models (SSM, FK, PU, LZ), pp. 4333–4342.
ICML-2019-MaoFRAFW #estimation #graph #order #probability: A Baseline for Any Order Gradient Estimation in Stochastic Computation Graphs (JM, JNF, TR, MAS, GF, SW), pp. 4343–4351.
ICML-2019-MarafiotiPHM #generative #synthesis: Adversarial Generation of Time-Frequency Features with application in audio synthesis (AM, NP, NH, PM), pp. 4352–4362.
ICML-2019-MaronFSL #invariant #network #on the: On the Universality of Invariant Networks (HM, EF, NS, YL), pp. 4363–4371.
ICML-2019-MartensCY #modelling #process: Decomposing feature-level variation with Covariate Gaussian Process Latent Variable Models (KM, KRC, CY), pp. 4372–4381.
ICML-2019-MaryCK #learning: Fairness-Aware Learning for Continuous Attributes and Treatments (JM, CC, NEK), pp. 4382–4391.
ICML-2019-MathiasenLG: Optimal Minimal Margin Maximization with Boosting (AM, KGL, AG), pp. 4392–4401.
ICML-2019-MathieuRST: Disentangling Disentanglement in Variational Autoencoders (EM, TR, NS0, YWT), pp. 4402–4412.
ICML-2019-MatteiF #generative #modelling #named #semistructured data #set: MIWAE: Deep Generative Modelling and Imputation of Incomplete Data Sets (PAM, JF), pp. 4413–4423.
ICML-2019-MavrinYKWY #learning #performance: Distributional Reinforcement Learning for Efficient Exploration (BM, HY, LK, KW, YY), pp. 4424–4434.
ICML-2019-McKennaSM #difference #estimation #modelling #privacy: Graphical-model based estimation and inference for differential privacy (RM, DS, GM), pp. 4435–4444.
ICML-2019-RoederGPDM #performance: Efficient Amortised Bayesian Inference for Hierarchical and Nonlinear Dynamical Systems (GR, PKG, AP, ND, EM), pp. 4445–4455.
ICML-2019-MehrotraCV #online #towards: Toward Controlling Discrimination in Online Ad Auctions (LEC, AM, NKV), pp. 4456–4465.
ICML-2019-MehtaCR #graph #network #probability: Stochastic Blockmodels meet Graph Neural Networks (NM, LC, PR), pp. 4466–4474.
ICML-2019-MeiQE: Imputing Missing Events in Continuous-Time Event Streams (HM, GQ, JE), pp. 4475–4485.
ICML-2019-MellerFAG #fault #network: Same, Same But Different: Recovering Neural Network Quantization Error Through Weight Factorization (EM, AF, UA, MG), pp. 4486–4495.
ICML-2019-MemoliSW: The Wasserstein Transform (FM, ZTS, ZW), pp. 4496–4504.
ICML-2019-MendisRAC #estimation #named #network #performance #throughput #using: Ithemal: Accurate, Portable and Fast Basic Block Throughput Estimation using Deep Neural Networks (CM, AR, SPA, MC), pp. 4505–4515.
ICML-2019-MenschBP #geometry #learning: Geometric Losses for Distributional Learning (AM, MB, GP), pp. 4516–4525.
ICML-2019-MercadoT0 #clustering #graph #matrix: Spectral Clustering of Signed Graphs via Matrix Power Means (PM0, FT, MH0), pp. 4526–4536.
ICML-2019-MetelT #optimisation #probability: Simple Stochastic Gradient Methods for Non-Smooth Non-Convex Regularized Optimization (MRM, AT), pp. 4537–4545.
ICML-2019-MetelliGR #configuration management #learning: Reinforcement Learning in Configurable Continuous Environments (AMM, EG, MR), pp. 4546–4555.
ICML-2019-MetzMNFS #comprehension: Understanding and correcting pathologies in the training of learned optimizers (LM, NM, JN, CDF, JSD), pp. 4556–4565.
ICML-2019-MeyerH #classification #kernel #performance #statistics: Optimality Implies Kernel Sum Classifiers are Statistically Efficient (RAM, JH), pp. 4566–4574.
ICML-2019-MianjyA #on the: On Dropout and Nuclear Norm Regularization (PM, RA), pp. 4575–4584.
ICML-2019-MillerOCM #modelling: Discriminative Regularization for Latent Variable Models with Applications to Electrocardiography (ACM, ZO, JPC, SM), pp. 4585–4594.
ICML-2019-MirshaniRS #functional #privacy: Formal Privacy for Functional Data with Gaussian Perturbations (AM, MR, ABS), pp. 4595–4604.
ICML-2019-MishneCC #learning: Co-manifold learning with missing data (GM, ECC, RRC), pp. 4605–4614.
ICML-2019-MohriSS #learning: Agnostic Federated Learning (MM, GS, ATS), pp. 4615–4625.
ICML-2019-MollenhoffC #generative #metric #modelling: Flat Metric Minimization with Applications in Generative Modeling (TM, DC), pp. 4626–4635.
ICML-2019-MoonAS #black box #combinator #optimisation #performance: Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization (SM, GA, HOS), pp. 4636–4645.
ICML-2019-MostafaW #network #parametricity #performance: Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization (HM, XW), pp. 4646–4655.
ICML-2019-MuehlebachJ: A Dynamical Systems Perspective on Nesterov Acceleration (MM, MIJ), pp. 4656–4662.
ICML-2019-Murphy0R0 #graph #relational: Relational Pooling for Graph Representations (RLM, BS0, VAR, BR0), pp. 4663–4673.
ICML-2019-NabiMS #learning #policy: Learning Optimal Fair Policies (RN, DM, IS), pp. 4674–4682.
ICML-2019-NacsonGLSS #modelling: Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models (MSN, SG, JDL, NS, DS), pp. 4683–4692.
ICML-2019-NaganoY0K #learning: A Wrapped Normal Distribution on Hyperbolic Space for Gradient-Based Learning (YN, SY, YF0, MK), pp. 4693–4702.
ICML-2019-Nagaraj0N: SGD without Replacement: Sharper Rates for General Smooth Convex Functions (DN, PJ0, PN), pp. 4703–4711.
ICML-2019-NalisnickHS: Dropout as a Structured Shrinkage Prior (ETN, JMHL, PS), pp. 4712–4722.
ICML-2019-NalisnickMTGL #hybrid #modelling: Hybrid Models with Deep and Invertible Features (ETN, AM, YWT, DG, BL), pp. 4723–4732.
ICML-2019-NamKMPSF #classification #learning #multi #permutation: Learning Context-dependent Label Permutations for Multi-label Classification (JN, YBK, ELM, SP, RS, JF), pp. 4733–4742.
ICML-2019-NayakMSRC #network: Zero-Shot Knowledge Distillation in Deep Networks (GKN, KRM, VS, VBR, AC), pp. 4743–4751.
ICML-2019-NayebiMP #embedded #framework #optimisation: A Framework for Bayesian Optimization in Embedded Subspaces (AN, AM, MP), pp. 4752–4761.
ICML-2019-NayerNV #matrix #metric #rank: Phaseless PCA: Low-Rank Matrix Recovery from Column-wise Phaseless Measurements (SN, PN, NV), pp. 4762–4770.
ICML-2019-NdiayeLFST #complexity #grid: Safe Grid Search with Optimal Complexity (EN, TL, OF, JS, IT), pp. 4771–4780.
ICML-2019-NedelecKP #learning: Learning to bid in revenue-maximizing auctions (TN, NEK, VP), pp. 4781–4789.
ICML-2019-Nguyen #learning #on the #set: On Connected Sublevel Sets in Deep Learning (QN), pp. 4790–4799.
ICML-2019-NguyenLKB #detection #multi #predict: Anomaly Detection With Multiple-Hypotheses Predictions (DTN, ZL, MK, TB), pp. 4800–4809.
ICML-2019-NguyenSR #analysis #monte carlo #optimisation: Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization (THN, US, GR), pp. 4810–4819.
ICML-2019-NirwanB #invariant: Rotation Invariant Householder Parameterization for Bayesian PCA (RSN, NB), pp. 4820–4828.
ICML-2019-NockW #integer: Lossless or Quantized Boosting with Integer Arithmetic (RN, RCW), pp. 4829–4838.
ICML-2019-NoklandE #fault #network: Training Neural Networks with Local Error Signals (AN, LHE), pp. 4839–4850.
ICML-2019-NovatiK #experience: Remember and Forget for Experience Replay (GN, PK), pp. 4851–4860.
ICML-2019-NyeHTS #learning #sketching: Learning to Infer Program Sketches (MIN, LBH, JBT, ASL), pp. 4861–4870.
ICML-2019-ObermeyerBJPCRG #graph: Tensor Variable Elimination for Plated Factor Graphs (FO, EB, MJ, NP, JC, AMR, NDG), pp. 4871–4880.
ICML-2019-OberstS #evaluation #modelling: Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models (MO, DAS), pp. 4881–4890.
ICML-2019-OchsM: Model Function Based Conditional Gradient Method with Armijo-like Line Search (PO, YM), pp. 4891–4900.
ICML-2019-OdenaOAG #debugging #fuzzing #named #network: TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing (AO, CO, DA, IJG), pp. 4901–4911.
ICML-2019-OglicG #kernel #learning #scalability: Scalable Learning in Reproducing Kernel Krein Spaces (DO, TG0), pp. 4912–4921.
ICML-2019-OonoS #approximate #estimation #network #parametricity: Approximation and non-parametric estimation of ResNet-type convolutional neural networks (KO, TS), pp. 4922–4931.
ICML-2019-OprescuSW #orthogonal #random: Orthogonal Random Forest for Causal Inference (MO, VS, ZSW), pp. 4932–4941.
ICML-2019-OsamaZS: Inferring Heterogeneous Causal Effects in Presence of Spatial Confounding (MO, DZ, TBS), pp. 4942–4950.
ICML-2019-OymakS #learning #question: Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path? (SO, MS), pp. 4951–4960.
ICML-2019-PanageasPW #algorithm #convergence #distributed #higher-order #multi #optimisation: Multiplicative Weights Updates as a distributed constrained optimization algorithm: Convergence to second-order stationary points almost always (IP, GP, XW), pp. 4961–4969.
ICML-2019-PangXDCZ #robust: Improving Adversarial Robustness via Promoting Ensemble Diversity (TP, KX, CD, NC, JZ0), pp. 4970–4979.
ICML-2019-PanousisCT #contest #network #parametricity: Nonparametric Bayesian Deep Networks with Local Competition (KPP, SC, ST), pp. 4980–4988.
ICML-2019-PapiniMLR #multi #optimisation #policy: Optimistic Policy Optimization via Multiple Importance Sampling (MP, AMM, LL, MR), pp. 4989–4999.
ICML-2019-PappasH #generative: Deep Residual Output Layers for Neural Language Generation (NP0, JH), pp. 5000–5011.
ICML-2019-Papyan #metric: Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians (VP), pp. 5012–5021.
ICML-2019-Parizi0ASF: Generalized Majorization-Minimization (SNP, KH0, RA, SS, PFF), pp. 5022–5031.
ICML-2019-ParkKK: Variational Laplace Autoencoders (YSP, CDK, GK), pp. 5032–5041.
ICML-2019-ParkSLS #empirical #network #probability: The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study (DSP, JSD, QVL, SLS), pp. 5042–5051.
ICML-2019-ParkYYS #approximate: Spectral Approximate Inference (SP, EY, SYY, JS), pp. 5052–5061.
ICML-2019-PathakG0 #self: Self-Supervised Exploration via Disagreement (DP, DG, AG0), pp. 5062–5071.
ICML-2019-PatyC #robust: Subspace Robust Wasserstein Distances (FPP, MC), pp. 5072–5081.
ICML-2019-PaulOW #learning #optimisation #policy #robust: Fingerprint Policy Optimisation for Robust Reinforcement Learning (SP, MAO, SW), pp. 5082–5091.
ICML-2019-0001HLZZ #clustering #multi #named #parametricity: COMIC: Multi-view Clustering Without Parameter Selection (XP0, ZH, JL, HZ, JTZ), pp. 5092–5101.
ICML-2019-PengHSS #learning: Domain Agnostic Learning with Disentangled Representations (XP, ZH, XS, KS), pp. 5102–5112.
ICML-2019-PengWCH #collaboration #network: Collaborative Channel Pruning for Deep Networks (HP, JW, SC, JH), pp. 5113–5122.
ICML-2019-PerraultPV #nondeterminism #performance: Exploiting structure of uncertainty for efficient matroid semi-bandits (PP, VP, MV), pp. 5123–5132.
ICML-2019-PetersonB0GR #predict: Cognitive model priors for predicting human decisions (JCP, DB, DR0, TLG, SJR), pp. 5133–5141.
ICML-2019-PhuongL #comprehension #towards: Towards Understanding Knowledge Distillation (MP, CL), pp. 5142–5151.
ICML-2019-PiergiovanniR: Temporal Gaussian Mixture Layer for Videos (AJP, MSR), pp. 5152–5161.
ICML-2019-PolianskiiP #approach #bound #classification #geometry #integration #monte carlo: Voronoi Boundary Classification: A High-Dimensional Geometric Approach via Weighted Monte Carlo Integration (VP, FTP), pp. 5162–5170.
ICML-2019-PooleOOAT #bound #on the: On Variational Bounds of Mutual Information (BP, SO, AvdO, AA, GT), pp. 5171–5180.
ICML-2019-PurohitGR #nondeterminism: Hiring Under Uncertainty (MP, SG, MR), pp. 5181–5189.
ICML-2019-QianQR: SAGA with Arbitrary Sampling (XQ, ZQ, PR), pp. 5190–5199.
ICML-2019-QianRGSLS #analysis: SGD with Arbitrary Sampling: General Analysis and Improved Rates (XQ, PR, RMG, AS, NL, ES), pp. 5200–5209.
ICML-2019-QianZCYH #named: AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss (KQ, YZ, SC, XY, MHJ), pp. 5210–5219.
ICML-2019-QiaoAZX #fault tolerance #machine learning: Fault Tolerance in Iterative-Convergent Machine Learning (AQ, BA, BZ, EPX), pp. 5220–5230.
ICML-2019-QinCCGR #automation #recognition #robust #speech: Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition (YQ, NC, GWC, IJG, CR), pp. 5231–5240.
ICML-2019-QuBT #graph #markov #named #network: GMNN: Graph Markov Neural Networks (MQ, YB, JT0), pp. 5241–5250.
ICML-2019-QuMX #learning: Nonlinear Distributional Gradient Temporal-Difference Learning (CQ, SM, HX), pp. 5251–5260.
ICML-2019-RadanovicDPS #learning #markov #process: Learning to Collaborate in Markov Decision Processes (GR, RD, DCP, AS), pp. 5261–5270.
ICML-2019-RaeBL: Meta-Learning Neural Bloom Filters (JWR, SB, TPL), pp. 5271–5280.
ICML-2019-RaghuBSOKMK #nondeterminism #predict: Direct Uncertainty Prediction for Medical Second Opinions (MR, KB, RS, ZO, RDK, SM, JMK), pp. 5281–5290.
ICML-2019-RaghunathanCJ #game studies #optimisation: Game Theoretic Optimization via Gradient-based Nikaido-Isoda Function (AUR, AC, DKJ), pp. 5291–5300.
ICML-2019-RahamanBADLHBC #bias #network #on the: On the Spectral Bias of Neural Networks (NR, AB, DA, FD, ML, FAH, YB, ACC), pp. 5301–5310.
ICML-2019-RahmanJG #compilation #network: Look Ma, No Latent Variables: Accurate Cutset Networks via Compilation (TR, SJ, VG), pp. 5311–5320.
ICML-2019-RajputFCLP #question: Does Data Augmentation Lead to Positive Margin? (SR, ZF, ZBC, PLL, DSP), pp. 5321–5330.
ICML-2019-RakellyZFLQ #learning #performance #probability: Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables (KR, AZ, CF, SL, DQ), pp. 5331–5340.
ICML-2019-RakotomamonjyGS: Screening rules for Lasso with non-convex Sparse Regularizers (AR, GG, JS), pp. 5341–5350.
ICML-2019-RamamurthyVM #bound #data analysis: Topological Data Analysis of Decision Boundaries with Application to Model Selection (KNR, KRV, KM), pp. 5351–5360.
ICML-2019-RatzlaffL #generative #named #network: HyperGAN: A Generative Model for Diverse, Performant Neural Networks (NR, FL), pp. 5361–5369.
ICML-2019-Ravi #modelling #performance #using: Efficient On-Device Models using Neural Projections (SR), pp. 5370–5379.
ICML-2019-Raziperchikolaei #coordination #estimation #parametricity: A Block Coordinate Descent Proximal Method for Simultaneous Filtering and Parameter Estimation (RR, HSB), pp. 5380–5388.
ICML-2019-RechtRSS #classification #question: Do ImageNet Classifiers Generalize to ImageNet? (BR, RR, LS, VS), pp. 5389–5400.
ICML-2019-ReeveK #classification #performance #robust #symmetry: Fast Rates for a kNN Classifier Robust to Unknown Asymmetric Label Noise (HWJR, AK), pp. 5401–5409.
ICML-2019-RenTQZZL #automation #recognition #speech: Almost Unsupervised Text to Speech and Automatic Speech Recognition (YR, XT, TQ, SZ, ZZ, TYL), pp. 5410–5419.
ICML-2019-RenZE #adaptation #reduction: Adaptive Antithetic Sampling for Variance Reduction (HR, SZ, SE), pp. 5420–5428.
ICML-2019-ReslerM #learning #online: Adversarial Online Learning with noise (AR, YM), pp. 5429–5437.
ICML-2019-RezaeiG #polynomial #process: A Polynomial Time MCMC Method for Sampling from Continuous Determinantal Point Processes (AR, SOG), pp. 5438–5447.
ICML-2019-RieckBB #classification #graph #persistent: A Persistent Weisfeiler-Lehman Procedure for Graph Classification (BR, CB, KMB), pp. 5448–5458.
ICML-2019-RollandKISC #learning #performance #probability #testing: Efficient learning of smooth probability functions from Bernoulli tests with guarantees (PR, AK, AI, AS, VC), pp. 5459–5467.
ICML-2019-Romoff0TOPB: Separable value functions across time-scales (JR, PH0, AT, YO, JP, EB), pp. 5468–5477.
ICML-2019-RosenbergM #markov #online #optimisation #process: Online Convex Optimization in Adversarial Markov Decision Processes (AR0, YM), pp. 5478–5486.
ICML-2019-RossiMF #modelling: Good Initializations of Variational Bayes for Deep Models (SR, PM, MF), pp. 5487–5497.
ICML-2019-RothKH #detection #statistics: The Odds are Odd: A Statistical Test for Detecting Adversarial Examples (KR, YK, TH), pp. 5498–5507.
ICML-2019-RotskoffJBV: Neuron birth-death dynamics accelerates gradient descent and converges asymptotically (GMR, SJ, JB, EVE), pp. 5508–5517.
ICML-2019-RouletDSH #algorithm #complexity: Iterative Linearized Control: Stable Algorithms and Complexity Guarantees (VR, DD, SSS, ZH), pp. 5518–5527.
ICML-2019-RowlandDKMBD #learning #statistics: Statistics and Samples in Distributional Reinforcement Learning (MR, RD, SK, RM, MGB, WD), pp. 5528–5536.
ICML-2019-RuizT: A Contrastive Divergence for Combining Variational Inference and MCMC (FJRR, MKT), pp. 5537–5545.
ICML-2019-RyuLWCWY: Plug-and-Play Methods Provably Converge with Properly Trained Denoisers (EKR, JL0, SW, XC, ZW, WY), pp. 5546–5557.
ICML-2019-SablayrollesDSO #black box: White-box vs Black-box: Bayes Optimal Strategies for Membership Inference (AS, MD, CS, YO, HJ), pp. 5558–5567.
ICML-2019-SafaviB #graph #multi: Tractable n-Metrics for Multiple Graphs (SS, JB), pp. 5568–5578.
ICML-2019-SajedS #algorithm: An Optimal Private Stochastic-MAB Algorithm based on Optimal Private Stopping Rule (TS, OS), pp. 5579–5588.
ICML-2019-SalimbeniDHD #process: Deep Gaussian Processes with Importance-Weighted Variational Inference (HS, VD, JH, MPD), pp. 5589–5598.
ICML-2019-SantiagoS #multi #optimisation: Multivariate Submodular Optimization (RS, FBS), pp. 5599–5609.
ICML-2019-SarkarR #finite #identification #linear: Near optimal finite time identification of arbitrary linear dynamical systems (TS, AR), pp. 5610–5618.
ICML-2019-SatoILT #adaptation #classification #co-evolution: Breaking Inter-Layer Co-Adaptation by Classifier Anonymization (IS, KI, GL, MT), pp. 5619–5627.
ICML-2019-SaunshiPAKK #analysis #learning #representation: A Theoretical Analysis of Contrastive Unsupervised Representation Learning (NS, OP, SA, MK, HK), pp. 5628–5637.
ICML-2019-ScheinWSZW #modelling: Locally Private Bayesian Inference for Count Models (AS, ZSW, AS, MZ, HMW), pp. 5638–5648.
ICML-2019-SchroeterSM #learning #locality: Weakly-Supervised Temporal Localization via Occurrence Count Learning (JS, KAS, ADM), pp. 5649–5659.
ICML-2019-SeshadriPU: Discovering Context Effects from Raw Choice Data (AS, AP, JU), pp. 5660–5669.
ICML-2019-ShahGAD #bias #learning #on the: On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference (RS, NG, PA, ADD), pp. 5670–5679.
ICML-2019-ShaniEM #learning #revisited: Exploration Conscious Reinforcement Learning Revisited (LS, YE, SM), pp. 5680–5689.
ICML-2019-SharanTBV #performance #rank: Compressed Factorization: Fast and Accurate Low-Rank Factorization of Compressively-Sensed Data (VS, KST, PB, GV), pp. 5690–5700.
ICML-2019-ShenHCD #independence #network #testing: Conditional Independence in Testing Bayesian Networks (YS, HH, AC, AD), pp. 5701–5709.
ICML-2019-ShenLL #learning: Learning to Clear the Market (WS, SL, RPL), pp. 5710–5718.
ICML-2019-ShenOAR #modelling: Mixture Models for Diverse Machine Translation: Tricks of the Trade (TS, MO, MA, MR), pp. 5719–5728.
ICML-2019-ShenRHQM #policy: Hessian Aided Policy Gradient (ZS, AR, HH, HQ, CM), pp. 5729–5738.
ICML-2019-ShenS #learning: Learning with Bad Training Data via Iterative Trimmed Loss Minimization (YS, SS), pp. 5739–5748.
ICML-2019-ShestopaloffD #monte carlo: Replica Conditional Sequential Monte Carlo (AS, AD), pp. 5749–5757.
ICML-2019-ShiK0 #modelling #network #scalability: Scalable Training of Inference Networks for Gaussian-Process Models (JS, MEK, JZ0), pp. 5758–5768.
ICML-2019-Shi0 #learning #multi #performance: Fast Direct Search in an Optimally Compressed Continuous Target Space for Efficient Multi-Label Active Learning (WS, QY0), pp. 5769–5778.
ICML-2019-ShyamJG #modelling: Model-Based Active Exploration (PS, WJ, FG), pp. 5779–5788.
ICML-2019-SiminelakisRBCL #evaluation #kernel: Rehashing Kernel Evaluation in High Dimensions (PS, KR, PB, MC, PL), pp. 5789–5798.
ICML-2019-SimonWR #generative #modelling #precise: Revisiting precision recall definition for generative modeling (LS, RW, JR), pp. 5799–5808.
ICML-2019-Simon-GabrielOB #first-order #network: First-Order Adversarial Vulnerability of Neural Networks and Input Dimension (CJSG, YO, LB, BS, DLP), pp. 5809–5817.
ICML-2019-SimonovFGP #complexity: Refined Complexity of PCA with Outliers (KS, FVF, PAG, FP), pp. 5818–5826.
ICML-2019-SimsekliSG #analysis #network #probability: A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks (US, LS, MG), pp. 5827–5837.
ICML-2019-SinghTJGB #generative #network #parametricity: Non-Parametric Priors For Generative Adversarial Networks (RS, PKT, SJ, RG, MWB), pp. 5838–5847.
ICML-2019-SinglaWFF #approximate #comprehension #higher-order #learning: Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation (SS0, EW, SF, SF), pp. 5848–5856.
ICML-2019-SlimCAV #framework #kernel #named: kernelPSI: a Post-Selection Inference Framework for Nonlinear Variable Selection (LS, CC0, CAA, JPV), pp. 5857–5865.
ICML-2019-SmithFRM #geometry #named: GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects (EJS, SF, AR, DM), pp. 5866–5876.
ICML-2019-SoLL: The Evolved Transformer (DRS, QVL, CL), pp. 5877–5886.
ICML-2019-SonKKHY #learning #multi #named: QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning (KS, DK, WJK, DH, YY), pp. 5887–5896.
ICML-2019-SongDKF: Distribution calibration for regression (HS, TD, MK, PAF), pp. 5897–5906.
ICML-2019-SongK0 #learning #named #robust: SELFIE: Refurbishing Unclean Samples for Robust Deep Learning (HS, MK, JGL0), pp. 5907–5915.
ICML-2019-SongPC #perspective: Revisiting the Softmax Bellman Operator: New Benefits and New Perspective (ZS, RP, LC), pp. 5916–5925.
ICML-2019-SongTQLL #generative #named #sequence: MASS: Masked Sequence to Sequence Pre-training for Language Generation (KS, XT, TQ, JL, TYL), pp. 5926–5936.
ICML-2019-SotoLF #3d #distributed #matrix #multi #polynomial: Dual Entangled Polynomial Code: Three-Dimensional Coding for Distributed Matrix Multiplication (PS, JL, XF), pp. 5937–5945.
ICML-2019-SpringKMS #sketching: Compressing Gradient Optimizers via Count-Sketches (RS, AK, VM, AS), pp. 5946–5955.
ICML-2019-StaibRKKS #adaptation: Escaping Saddle Points with Adaptive Gradient Methods (MS, SJR, SK, SK, SS), pp. 5956–5965.
ICML-2019-StelznerPK #modelling #performance #probability: Faster Attend-Infer-Repeat with Tractable Probabilistic Models (KS, RP, KK), pp. 5966–5975.
ICML-2019-SternCKU #flexibility #generative #sequence: Insertion Transformer: Flexible Sequence Generation via Insertion Operations (MS, WC, JK, JU), pp. 5976–5985.
ICML-2019-Stickland0 #adaptation #learning #multi #performance: BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning (ACS, IM0), pp. 5986–5995.
ICML-2019-Streeter #learning #linear: Learning Optimal Linear Regularizers (MS), pp. 5996–6004.
ICML-2019-SuWSJ #adaptation #evaluation #learning #named #policy: CAB: Continuous Adaptive Blending for Policy Evaluation and Learning (YS, LW, MS, TJ), pp. 6005–6014.
ICML-2019-SuW #distance #learning #metric #sequence: Learning Distance for Sequences by Learning a Ground Metric (BS, YW), pp. 6015–6025.
ICML-2019-SunBD0M #memory management: Contextual Memory Trees (WS, AB, HDI, JL0, PM), pp. 6026–6035.
ICML-2019-0002VBB #learning #performance: Provably Efficient Imitation Learning from Observation Alone (WS0, AV, BB, DB), pp. 6036–6045.
ICML-2019-SundinSSVSK #learning: Active Learning for Decision-Making from Imbalanced Observational Data (IS, PS, ES, AV, SS, SK), pp. 6046–6055.
ICML-2019-SuterMSB #robust #validation: Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness (RS, ÐM, BS, SB), pp. 6056–6065.
ICML-2019-0008TO #graph: Hyperbolic Disk Embeddings for Directed Acyclic Graphs (RS0, RT, SO), pp. 6066–6075.
ICML-2019-TaghvaeiM #probability: Accelerated Flow for Probability Distributions (AT, PGM), pp. 6076–6085.
ICML-2019-TaiBV #network: Equivariant Transformer Networks (KST, PB, GV), pp. 6086–6095.
ICML-2019-TallecBO #robust: Making Deep Q-learning methods robust to time discretization (CT, LB, YO), pp. 6096–6104.
ICML-2019-TanL #named #network #scalability: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (MT, QVL), pp. 6105–6114.
ICML-2019-TanP: Hierarchical Decompositional Mixtures of Variational Autoencoders (PLT, RP), pp. 6115–6124.
ICML-2019-Tang #modelling #ranking: Mallows ranking models: maximum likelihood estimate and regeneration (WT), pp. 6125–6134.
ICML-2019-TangLJR #correlation: Correlated Variational Auto-Encoders (DT, DL, TJ, NR), pp. 6135–6144.
ICML-2019-TangR #predict: The Variational Predictive Natural Gradient (DT, RR), pp. 6145–6154.
ICML-2019-TangYLZL #named #parallel #probability: DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-pass Error-Compensated Compression (HT, CY, XL, TZ, JL0), pp. 6155–6165.
ICML-2019-TannoAACN #adaptation: Adaptive Neural Trees (RT, KA, DCA, AC, AVN), pp. 6166–6175.
ICML-2019-TaoDCBCLZBC #perspective: Variational Annealing of GANs: A Langevin Perspective (CT, SD, LC, KB, JC, CL0, RZ, GVB, LC), pp. 6176–6185.
ICML-2019-TavaresBMSR #declarative: Predicate Exchange: Inference with Declarative Knowledge (ZT, JB, EM, ASL, RR), pp. 6186–6195.
ICML-2019-TennenholtzM #natural language: The Natural Language of Actions (GT, SM), pp. 6196–6205.
ICML-2019-TeradaY #kernel #normalisation: Kernel Normalized Cut: a Theoretical Revisit (YT, MY), pp. 6206–6214.
ICML-2019-TesslerEM #learning #robust: Action Robust Reinforcement Learning and Applications in Continuous Control (CT, YE, SM), pp. 6215–6224.
ICML-2019-ThomasL: Concentration Inequalities for Conditional Value at Risk (PST, EGLM), pp. 6225–6233.
ICML-2019-ThulasidasanBBC #learning #using: Combating Label Noise in Deep Learning using Abstention (ST, TB, JAB, GC, JMY), pp. 6234–6243.
ICML-2019-TianMGSCPZ #analysis: ELF OpenGo: an analysis and open reimplementation of AlphaZero (YT, JM, QG, SS, ZC, JP, LZ), pp. 6244–6253.
ICML-2019-TiomokoCBG #estimation #matrix #metric #random #scalability: Random Matrix Improved Covariance Estimation for a Large Class of Metrics (MT, RC, FB, GG), pp. 6254–6263.
ICML-2019-TirinzoniSR #multi #policy: Transfer of Samples in Policy Search via Multiple Importance Sampling (AT, MS, MR), pp. 6264–6274.
ICML-2019-VayerCTCF #graph: Optimal Transport for structured data with application on graphs (TV, NC, RT, LC, RF), pp. 6275–6284.
ICML-2019-TongC #multi: Discovering Latent Covariance Structures for Multiple Time Series (AT, JC), pp. 6285–6294.
ICML-2019-TranDRC #generative #learning: Bayesian Generative Active Deep Learning (TT, TTD, IDR0, GC), pp. 6295–6304.
ICML-2019-TranKSK #named #network #using: DeepNose: Using artificial neural networks to represent the space of odorants (NBT, DRK, SS, AAK), pp. 6305–6314.
ICML-2019-TrippeHAB #approximate #named #rank #using: LR-GLM: High-Dimensional Bayesian Inference Using Low-Rank Data Approximations (BLT, JHH, RA, TB), pp. 6315–6324.
ICML-2019-TrouleauEGKT #learning #process: Learning Hawkes Processes Under Synchronization Noise (WT, JE, MG, NK, PT), pp. 6325–6334.
ICML-2019-TsakirisP: Homomorphic Sensing (MCT, LP), pp. 6335–6344.
ICML-2019-TurnerHFSY #generative #network: Metropolis-Hastings Generative Adversarial Networks (RDT, JH, EF, YS, JY), pp. 6345–6353.
ICML-2019-TzengW #detection #distributed #graph: Distributed, Egocentric Representations of Graphs for Detecting Critical Structures (RCT, SHW), pp. 6354–6362.
ICML-2019-Upadhyay #algorithm #sublinear: Sublinear Space Private Algorithms Under the Sliding Window Model (JU), pp. 6363–6372.
ICML-2019-UstunLP #classification: Fairness without Harm: Decoupled Classifiers with Preference Guarantees (BU, YL0, DCP), pp. 6373–6382.
ICML-2019-UurtioBR #analysis #canonical #correlation #kernel #scalability: Large-Scale Sparse Kernel Canonical Correlation Analysis (VU, SB, JR), pp. 6383–6391.
ICML-2019-DijkNNP #convergence: Characterization of Convex Objective Functions and Optimal Expected Convergence Rates for SGD (MvD, LMN, PHN, DTP), pp. 6392–6400.
ICML-2019-NiekerkJER #learning: Composing Value Functions in Reinforcement Learning (BvN, SJ, ACE, BR), pp. 6401–6409.
ICML-2019-VargasBH #comparison #difference #semantics: Model Comparison for Semantic Grouping (FV, KB, NH), pp. 6410–6417.
ICML-2019-VarmaSHRR #dependence #learning #modelling: Learning Dependency Structures for Weak Supervision Models (PV, FS, AH, AR, CR), pp. 6418–6427.
ICML-2019-VedantamDLRBP #modelling #probability #visual notation: Probabilistic Neural Symbolic Models for Interpretable Visual Question Answering (RV, KD, SL, MR, DB, DP), pp. 6428–6437.
ICML-2019-VermaLBNMLB: Manifold Mixup: Better Representations by Interpolating Hidden States (VV, AL, CB, AN, IM, DLP, YB), pp. 6438–6447.
ICML-2019-VinayakKVK #estimation #learning #parametricity: Maximum Likelihood Estimation for Learning Populations of Parameters (RKV, WK, GV, SMK), pp. 6448–6457.
ICML-2019-VladimirovaVMA #comprehension #network: Understanding Priors in Bayesian Neural Networks at the Unit Level (MV, JV, PM, JA), pp. 6458–6467.
ICML-2019-VlassisBDJ #design #evaluation #on the: On the Design of Estimators for Bandit Off-Policy Evaluation (NV, AB, MD, TJ), pp. 6468–6476.
ICML-2019-VorobevUGS #learning #ranking: Learning to select for a predefined ranking (AV, AU, GG, PS), pp. 6477–6486.
ICML-2019-WagstaffFEPO #on the #representation #set: On the Limitations of Representing Functions on Sets (EW, FF, ME, IP, MAO), pp. 6487–6494.
ICML-2019-WalkerG #graph #process: Graph Convolutional Gaussian Processes (IW, BG), pp. 6495–6504.
ICML-2019-Wang #low cost: Gaining Free or Low-Cost Interpretability with Interpretable Partial Substitute (TW), pp. 6505–6514.
ICML-2019-Wang0XZ #network: Convolutional Poisson Gamma Belief Network (CW, BC0, SX, MZ), pp. 6515–6525.
ICML-2019-WangC0 #empirical: Differentially Private Empirical Risk Minimization with Non-convex Loss Functions (DW, CC, JX0), pp. 6526–6535.
ICML-2019-WangCAD #estimation #learning #policy #random: Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation (RW, CC, PVA, YD), pp. 6536–6544.
ICML-2019-WangDWK #learning #logic #named #reasoning #satisfiability #using: SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver (PWW, PLD, BW, JZK), pp. 6545–6554.
ICML-2019-WangG0 #modelling: Improving Neural Language Modeling via Adversarial Training (DW, CG, QL0), pp. 6555–6565.
ICML-2019-WangGFZ #named: EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis (CW, RBG, SF, GZ), pp. 6566–6575.
ICML-2019-Wang0 #learning #modelling: Nonlinear Stein Variational Gradient Descent for Learning Diversified Mixture Models (DW, QL0), pp. 6576–6585.
ICML-2019-WangM0YZG #convergence #on the #robust: On the Convergence and Robustness of Adversarial Training (YW0, XM, JB0, JY, BZ, QG), pp. 6586–6595.
ICML-2019-WangN #network: State-Regularized Recurrent Neural Networks (CW, MN), pp. 6596–6606.
ICML-2019-WangSMGFJ: Deep Factors for Forecasting (YW, AS, DCM, JG, DF, TJ), pp. 6607–6617.
ICML-2019-WangUC: Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributions (HW0, BU, FPC), pp. 6618–6627.
ICML-2019-Wang019a #difference #linear #on the #privacy: On Sparse Linear Regression in the Local Differential Privacy Model (DW, JX0), pp. 6628–6637.
ICML-2019-WangZ0Q #learning #random #recommendation #robust: Doubly Robust Joint Learning for Recommendation on Data Missing Not at Random (XW, RZ0, YS0, JQ0), pp. 6638–6647.
ICML-2019-WangZXS #learning #on the: On the Generalization Gap in Reparameterizable Reinforcement Learning (HW, SZ, CX, RS), pp. 6648–6658.
ICML-2019-WangZB #bias #matter #network: Bias Also Matters: Bias Attribution for Deep Neural Network Explanation (SW, TZ, JAB), pp. 6659–6667.
ICML-2019-WangZB19a #network: Jumpout : Improved Dropout for Deep Neural Networks with ReLUs (SW, TZ, JAB), pp. 6668–6676.
ICML-2019-WardWB #convergence: AdaGrad stepsizes: sharp convergence over nonconvex landscapes (RW, XW, LB), pp. 6677–6686.
ICML-2019-WeiDGG #linear #modelling: Generalized Linear Rule Models (DW, SD, TG, OG), pp. 6687–6696.
ICML-2019-WeiYW #generative #modelling #on the #statistics: On the statistical rate of nonlinear recovery in generative models with heavy-tailed data (XW, ZY, ZW), pp. 6697–6706.
ICML-2019-WeiszGS #algorithm #approximate #named: CapsAndRuns: An Improved Method for Approximately Optimal Algorithm Configuration (GW, AG, CS), pp. 6707–6715.
ICML-2019-WelleckBDC #generative: Non-Monotonic Sequential Text Generation (SW, KB, HDI, KC), pp. 6716–6726.
ICML-2019-WengCNSBOD #approach #named #network #probability #robust #verification: PROVEN: Verifying Robustness of Neural Networks with a Probabilistic Approach (LW, PYC, LMN, MSS, AB, IVO, LD), pp. 6727–6736.
ICML-2019-LiSSG #exponential #kernel #learning #product line: Learning deep kernels for exponential family densities (WL, DJS, HS, AG), pp. 6737–6746.
ICML-2019-WestphalB #testing: Improving Model Selection by Employing the Test Data (MW, WB), pp. 6747–6756.
ICML-2019-WhitehillR #automation #classification: Automatic Classifiers as Scientific Instruments: One Step Further Away from Ground-Truth (JW, AR), pp. 6757–6765.
ICML-2019-WildnerK #markov #process: Moment-Based Variational Inference for Markov Jump Processes (CW, HK), pp. 6766–6775.
ICML-2019-WilkinsonARSS #analysis #probability: End-to-End Probabilistic Inference for Nonstationary Audio Analysis (WJW, MRA, JDR, DS, AS), pp. 6776–6785.
ICML-2019-WilliamsonM #metric: Fairness risk measures (RCW, AKM), pp. 6786–6797.
ICML-2019-WiqvistMPF #approximate #architecture #learning #network #statistics #summary: Partially Exchangeable Networks and Architectures for Learning Summary Statistics in Approximate Bayesian Computation (SW, PAM, UP, JF), pp. 6798–6807.
ICML-2019-WongSK: Wasserstein Adversarial Examples via Projected Sinkhorn Iterations (EW, FRS, JZK), pp. 6808–6817.
ICML-2019-WuCBTS #learning: Imitation Learning from Imperfect Demonstration (YHW, NC, HB, VT, MS), pp. 6818–6827.
ICML-2019-WuDSYHSRK #learning #matrix #metric: Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling (SW, AD, SS, FXY, DNHR, DS, AR, SK), pp. 6828–6839.
ICML-2019-WuLZ #multi #optimisation #reuse: Heterogeneous Model Reuse via Optimizing Multiparty Multiclass Margin (XZW, SL, ZHZ), pp. 6840–6849.
ICML-2019-WuRL: Deep Compressed Sensing (YW, MR, TPL), pp. 6850–6860.
ICML-2019-WuSZFYW #graph #network: Simplifying Graph Convolutional Networks (FW, AHSJ, TZ, CF, TY, KQW), pp. 6861–6871.
ICML-2019-WuWKL #adaptation #symmetry: Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment (YW, EW, DK, ZCL), pp. 6872–6881.
ICML-2019-XieCJZZ #on the #performance #scalability: On Scalable and Efficient Computation of Large Scale Optimal Transport (YX, MC, HJ, TZ, HZ), pp. 6882–6892.
ICML-2019-XieKG #distributed #fault tolerance #named #probability: Zeno: Distributed Stochastic Gradient Descent with Suspicion-based Fault-tolerance (CX, SK, IG), pp. 6893–6901.
ICML-2019-XieWLZL: Differentiable Linearized ADMM (XX, JW, GL, ZZ, ZL), pp. 6902–6911.
ICML-2019-XingNL #approximate: Calibrated Approximate Bayesian Inference (HX, GN, JL), pp. 6912–6920.
ICML-2019-XuL #clustering: Power k-Means Clustering (JX, KL), pp. 6921–6931.
ICML-2019-XuLZC #graph #learning: Gromov-Wasserstein Learning for Graph Matching and Node Embedding (HX, DL, HZ, LC), pp. 6932–6941.
ICML-2019-XuQLJY #convergence #optimisation #probability: Stochastic Optimization for DC Functions and Non-smooth Non-convex Regularizers with Non-asymptotic Convergence (YX, QQ, QL, RJ, TY), pp. 6942–6951.
ICML-2019-XuRDLF #learning: Learning a Prior over Intent via Meta-Inverse Reinforcement Learning (KX, ER, ADD, SL, CF), pp. 6952–6962.
ICML-2019-XuSS: Variational Russian Roulette for Deep Bayesian Nonparametrics (KX, AS, CAS), pp. 6963–6972.
ICML-2019-YadavKMM #clustering #exponential: Supervised Hierarchical Clustering with Exponential Linkage (NY, AK, NM, AM), pp. 6973–6983.
ICML-2019-YangD #learning #proving #theorem: Learning to Prove Theorems via Interacting with Proof Assistants (KY, JD), pp. 6984–6994.
ICML-2019-YangW #parametricity #using: Sample-Optimal Parametric Q-Learning Using Linearly Additive Features (LY, MW), pp. 6995–7004.
ICML-2019-YangWLCXS0X #named #network #performance: LegoNet: Efficient Convolutional Neural Networks with Lego Filters (ZY, YW, CL, HC, CX, BS, CX0, CX0), pp. 7005–7014.
ICML-2019-YangZKBWS #precise #probability: SWALP : Stochastic Weight Averaging in Low Precision Training (GY, TZ, PK, JB, AGW, CDS), pp. 7015–7024.
ICML-2019-YangZXK #effectiveness #estimation #matrix #named #robust #towards: ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation (YY, GZ, ZX, DK), pp. 7025–7034.
ICML-2019-YaoK0 #performance: Efficient Nonconvex Regularized Tensor Completion with Structure-aware Proximal Iterations (QY, JTYK, BH0), pp. 7035–7044.
ICML-2019-YaoWHL: Hierarchically Structured Meta-learning (HY, YW, JH, ZL), pp. 7045–7054.
ICML-2019-0002WF #clustering #complexity #kernel #query: Tight Kernel Query Complexity of Kernel Ridge Regression and Kernel $k$-means Clustering (TY0, DPW, MF), pp. 7055–7063.
ICML-2019-YeS #comprehension #geometry: Understanding Geometry of Encoder-Decoder CNNs (JCY, WKS), pp. 7064–7073.
ICML-2019-YinCRB #distributed #learning: Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning (DY, YC0, KR, PLB), pp. 7074–7084.
ICML-2019-YinRB #complexity #robust: Rademacher Complexity for Adversarially Robust Generalization (DY, KR, PLB), pp. 7085–7094.
ICML-2019-YinYZ #category theory #named: ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables (MY, YY, MZ), pp. 7095–7104.
ICML-2019-YingKCR0H #architecture #named #towards: NAS-Bench-101: Towards Reproducible Neural Architecture Search (CY, AK, EC, ER, KM0, FH), pp. 7105–7114.
ICML-2019-YoonSM #adaptation #learning #named #network: TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning (SWY, JS, JM), pp. 7115–7123.
ICML-2019-YouWLJ #adaptation #towards: Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation (KY, XW, ML, MIJ), pp. 7124–7133.
ICML-2019-YouYL #graph #network: Position-aware Graph Neural Networks (JY, RY, JL), pp. 7134–7143.
ICML-2019-YoungBN #generative #learning #modelling #synthesis: Learning Neurosymbolic Generative Models via Program Synthesis (HY, OB, MN), pp. 7144–7153.
ICML-2019-YuCGY #graph #learning #named #network: DAG-GNN: DAG Structure Learning with Graph Neural Networks (YY, JC, TG, MY), pp. 7154–7163.
ICML-2019-Yu0YNTS #how #question: How does Disagreement Help Generalization against Label Corruption? (XY, BH0, JY, GN, IWT, MS), pp. 7164–7173.
ICML-2019-YuJ #communication #complexity #on the #optimisation #parallel #probability: On the Computation and Communication Complexity of Parallel SGD with Dynamic Batch Sizes for Stochastic Non-Convex Optimization (HY, RJ), pp. 7174–7183.
ICML-2019-YuJY #analysis #communication #distributed #linear #on the #optimisation #performance: On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimization (HY, RJ, SY), pp. 7184–7193.
ICML-2019-YuSE #learning #multi: Multi-Agent Adversarial Inverse Reinforcement Learning (LY, JS, SE), pp. 7194–7201.
ICML-2019-YuTRKSAZL #distributed #learning #network: Distributed Learning over Unreliable Networks (CY, HT, CR, SK, AS, DA, CZ, JL0), pp. 7202–7212.
ICML-2019-YuanL #adaptation #analysis #component #online: Online Adaptive Principal Component Analysis and Its extensions (JY, AGL), pp. 7213–7221.
ICML-2019-YuanLX #composition #generative #infinity #modelling #representation: Generative Modeling of Infinite Occluded Objects for Compositional Scene Representation (JY, BL, XX), pp. 7222–7231.
ICML-2019-YuanZLS #difference #modelling: Differential Inclusions for Modeling Nonsmooth ADMM Variants: A Continuous Limit Theory (HY, YZ, CJL, QS), pp. 7232–7241.
ICML-2019-YunZYLA #analysis #learning #optimisation #statistics: Trimming the l₁ Regularizer: Statistical Analysis, Optimization, and Applications to Deep Learning (JY, PZ, EY, ACL, AYA), pp. 7242–7251.
ICML-2019-YurochkinAGGHK #learning #network #parametricity: Bayesian Nonparametric Federated Learning of Neural Networks (MY, MA, SG, KHG, TNH, YK), pp. 7252–7261.
ICML-2019-YurochkinGSN #geometry: Dirichlet Simplex Nest and Geometric Inference (MY, AG, YS, XN), pp. 7262–7271.
ICML-2019-YurtseverFC #framework: A Conditional-Gradient-Based Augmented Lagrangian Framework (AY, OF, VC), pp. 7272–7281.
ICML-2019-YurtseverSC #difference #probability: Conditional Gradient Methods via Stochastic Path-Integrated Differential Estimator (AY, SS, VC), pp. 7282–7291.
ICML-2019-ZablockiBSPG #learning #recognition: Context-Aware Zero-Shot Learning for Object Recognition (EZ, PB, LS, BP, PG), pp. 7292–7303.
ICML-2019-ZanetteB #bound #learning #problem #using: Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds (AZ, EB), pp. 7304–7312.
ICML-2019-ZengLLY #convergence #coordination #learning: Global Convergence of Block Coordinate Descent in Deep Learning (JZ, TTKL, SL, YY0), pp. 7313–7323.
ICML-2019-Zhang #invariant #network: Making Convolutional Networks Shift-Invariant Again (RZ), pp. 7324–7334.
ICML-2019-ZhangAD0N #feedback #robust: Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback (CZ, AA, HDI, JL0, SN), pp. 7335–7344.
ICML-2019-ZhangCC: When Samples Are Strategically Selected (HZ, YC0, VC), pp. 7345–7353.
ICML-2019-ZhangGMO #generative #network #self: Self-Attention Generative Adversarial Networks (HZ0, IJG, DNM, AO), pp. 7354–7363.
ICML-2019-ZhangHK #design #distributed #graph #named #network: Circuit-GNN: Graph Neural Networks for Distributed Circuit Design (GZ, HH, DK), pp. 7364–7373.
ICML-2019-ZhangHY #learning #named #performance #recognition #visual notation: LatentGNN: Learning Efficient Non-local Relations for Visual Recognition (SZ, XH, SY), pp. 7374–7383.
ICML-2019-ZhangJHHL #clustering #collaboration: Neural Collaborative Subspace Clustering (TZ, PJ, MH, WbH, HL), pp. 7384–7393.
ICML-2019-ZhangL #incremental #kernel #learning #online #random #sketching: Incremental Randomized Sketching for Online Kernel Learning (XZ, SL), pp. 7394–7403.
ICML-2019-0002LLJ #adaptation #algorithm: Bridging Theory and Algorithm for Domain Adaptation (YZ0, TL, ML, MIJ), pp. 7404–7413.
ICML-2019-ZhangLZ #adaptation: Adaptive Regret of Convex and Smooth Functions (LZ0, TYL, ZHZ), pp. 7414–7423.
ICML-2019-ZhangP #correlation #modelling #random: Random Function Priors for Correlation Modeling (AZ, JWP), pp. 7424–7433.
ICML-2019-ZhangS #learning #network: Co-Representation Network for Generalized Zero-Shot Learning (FZ, GS), pp. 7434–7443.
ICML-2019-ZhangVSA0L #learning #modelling #named: SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning (MZ, SV, LS, PA, MJJ0, SL), pp. 7444–7453.
ICML-2019-ZhangX #incremental #random: A Composite Randomized Incremental Gradient Method (JZ, LX), pp. 7454–7462.
ICML-2019-ZhangY #estimation #modelling #multi #performance: Fast and Stable Maximum Likelihood Estimation for Incomplete Multinomial Models (CZ, GY), pp. 7463–7471.
ICML-2019-ZhangYJXGJ #robust #trade-off: Theoretically Principled Trade-off between Robustness and Accuracy (HZ, YY, JJ, EPX, LEG, MIJ), pp. 7472–7482.
ICML-2019-ZhangYT #learning #novel #policy: Learning Novel Policies For Tasks (YZ, WY, GT), pp. 7483–7492.
ICML-2019-ZhangZLWZ #algorithm #matrix #orthogonal: Greedy Orthogonal Pivoting Algorithm for Non-Negative Matrix Factorization (KZ, SZ, JL, JW, JZ), pp. 7493–7501.
ICML-2019-ZhangZ #network: Interpreting Adversarially Trained Convolutional Neural Networks (TZ, ZZ), pp. 7502–7511.
ICML-2019-ZhangZT #adaptation #monte carlo #multi #testing: Adaptive Monte Carlo Multiple Testing via Multi-Armed Bandits (MJZ, JZ, DT), pp. 7512–7522.
ICML-2019-0002CZG #adaptation #invariant #learning #on the: On Learning Invariant Representations for Domain Adaptation (HZ0, RTdC, KZ0, GJG), pp. 7523–7532.
ICML-2019-ZhaoFNG: Metric-Optimized Example Weights (SZ, MMF, HN, MRG), pp. 7533–7542.
ICML-2019-ZhaoHDSZ #network #using: Improving Neural Network Quantization without Retraining using Outlier Channel Splitting (RZ, YH, JD, CDS, ZZ), pp. 7543–7552.
ICML-2019-ZhaoST #learning #multi: Maximum Entropy-Regularized Multi-Goal Reinforcement Learning (RZ, XS0, VT), pp. 7553–7562.
ICML-2019-Zhou0Y #optimisation #probability: Stochastic Iterative Hard Thresholding for Graph-structured Sparsity Optimization (BZ, FC0, YY), pp. 7563–7573.
ICML-2019-ZhouG #bound #optimisation: Lower Bounds for Smooth Nonconvex Finite-Sum Optimization (DZ, QG), pp. 7574–7583.
ICML-2019-ZhouLSYW00Z #generative: Lipschitz Generative Adversarial Nets (ZZ, JL, YS, LY, HW, WZ0, YY0, ZZ), pp. 7584–7593.
ICML-2019-ZhouLLLZZ #comprehension #network #towards: Toward Understanding the Importance of Noise in Training Neural Networks (MZ, TL, YL, DL, EZ, TZ), pp. 7594–7602.
ICML-2019-ZhouYWP #approach #architecture #named: BayesNAS: A Bayesian Approach for Neural Architecture Search (HZ, MY, JW0, WP), pp. 7603–7613.
ICML-2019-ZhuHLTSG: Transferable Clean-Label Poisoning Attacks on Deep Neural Nets (CZ, WRH, HL, GT, CS, TG), pp. 7614–7623.
ICML-2019-ZhuSLHB #fault tolerance #graph #learning: Improved Dynamic Graph Learning through Fault-Tolerant Sparsification (CJZ, SS, KyL, SH, JB), pp. 7624–7633.
ICML-2019-ZhuW #difference #privacy: Poission Subsampled Rényi Differential Privacy (YZ0, YXW), pp. 7634–7642.
ICML-2019-ZhuWS #classification #learning: Learning Classifiers for Target Domain with Limited or No Labels (PZ, HW, VS), pp. 7643–7653.
ICML-2019-ZhuWYWM #behaviour #probability: The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects (ZZ, JW, BY, LW, JM), pp. 7654–7663.
ICML-2019-ZhuangCO #learning #online #optimisation #probability: Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization (ZZ, AC, FO), pp. 7664–7672.
ICML-2019-ZieglerR #normalisation #sequence: Latent Normalizing Flows for Discrete Sequences (ZMZ, AMR), pp. 7673–7682.
ICML-2019-ZimmertLW #probability: Beating Stochastic and Adversarial Semi-bandits Optimally and Simultaneously (JZ, HL, CYW), pp. 7683–7692.
ICML-2019-ZintgrafSKHW #adaptation #performance: Fast Context Adaptation via Meta-Learning (LMZ, KS, VK, KH, SW), pp. 7693–7702.
ICML-2019-ZrnicH #adaptation #data analysis: Natural Analysts in Adaptive Data Analysis (TZ, MH), pp. 7703–7711.

Kamalika Chaudhuri, Ruslan SalakhutdinovProceedings of the 36th International Conference on Machine LearningICML, 2019.

Contents (774 items)

Kamalika Chaudhuri, Ruslan Salakhutdinov
Proceedings of the 36th International Conference on Machine Learning
ICML, 2019.