BibSLEIGH — Proceedings of the 34th International Conference on Machine Learning

Doina Precup, Yee Whye Teh
Proceedings of the 34th International Conference on Machine Learning
ICML, 2017.

KER

@proceedings{ICML-2017,
	editor        = "Doina Precup and Yee Whye Teh",
	ee            = "http://proceedings.mlr.press/v70/",
	publisher     = "{PMLR}",
	series        = "{Proceedings of Machine Learning Research}",
	title         = "{Proceedings of the 34th International Conference on Machine Learning}",
	volume        = 70,
	year          = 2017,
}

Contents (434 items)

ICML-2017-AchabBGMM #multi: Uncovering Causality from Multivariate Hawkes Integrated Cumulants (MA, EB, SG, IM, JFM), pp. 1–10.
ICML-2017-AcharyaDOS #approach #symmetry: A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions (JA, HD, AO, ATS), pp. 11–21.
ICML-2017-AchiamHTA #optimisation #policy: Constrained Policy Optimization (JA, DH, AT, PA), pp. 22–31.
ICML-2017-AgarwalS #difference #learning #online #privacy: The Price of Differential Privacy for Online Learning (NA, KS), pp. 32–40.
ICML-2017-AkrourS0N #optimisation: Local Bayesian Optimization of Motor Skills (RA, DS, JP0, GN), pp. 41–50.
ICML-2017-AksoylarOS #detection: Connected Subgraph Detection with Mirror Descent on SDPs (CA, LO, VS), pp. 51–59.
ICML-2017-AlaaHS #learning #process: Learning from Clinical Judgments: Semi-Markov-Modulated Marked Hawkes Processes for Risk Prognosis (AMA, SH, MvdS), pp. 60–69.
ICML-2017-AliWK #performance #programming: A Semismooth Newton Method for Fast, Generic Convex Programming (AA, EW, JZK), pp. 70–79.
ICML-2017-AllamanisCKS #learning #semantics: Learning Continuous Semantic Representations of Symbolic Expressions (MA, PC, PK, CAS), pp. 80–88.
ICML-2017-Allen-Zhu #named #optimisation #parametricity #performance #probability: Natasha: Faster Non-Convex Stochastic Optimization via Strongly Non-Convex Parameter (ZAZ), pp. 89–97.
ICML-2017-Allen-ZhuL #performance: Doubly Accelerated Methods for Faster CCA and Generalized Eigendecomposition (ZAZ, YL), pp. 98–106.
ICML-2017-Allen-ZhuL17a #approximate #component #matrix #performance: Faster Principal Component Regression and Stable Matrix Chebyshev Approximation (ZAZ, YL), pp. 107–115.
ICML-2017-Allen-ZhuL17b #learning #online #performance: Follow the Compressed Leader: Faster Online Learning of Eigenvectors and Faster MMWU (ZAZ, YL), pp. 116–125.
ICML-2017-Allen-ZhuLSW #design: Near-Optimal Design of Experiments via Regret Minimization (ZAZ, YL, AS, YW), pp. 126–135.
ICML-2017-AmosK #named #network #optimisation: OptNet: Differentiable Optimization as a Layer in Neural Networks (BA, JZK), pp. 136–145.
ICML-2017-AmosXK #network: Input Convex Neural Networks (BA, LX, JZK), pp. 146–155.
ICML-2017-AndersonG #algorithm #approximate #online #performance #rank: An Efficient, Sparsity-Preserving, Online Algorithm for Low-Rank Approximation (DGA, MG0), pp. 156–165.
ICML-2017-AndreasKL #composition #learning #multi #policy #sketching: Modular Multitask Reinforcement Learning with Policy Sketches (JA, DK, SL), pp. 166–175.
ICML-2017-AnschelBS #learning #named #reduction: Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning (OA, NB, NS), pp. 176–185.
ICML-2017-AppelP #empirical #framework #multi: A Simple Multi-Class Boosting Framework with Theoretical Guarantees and Empirical Proficiency (RA, PP), pp. 186–194.
ICML-2017-ArikCCDGKLMNRSS #realtime: Deep Voice: Real-time Neural Text-to-Speech (SÖA, MC, AC, GFD, AG, YK, XL, JM, AYN, JR, SS, MS), pp. 195–204.
ICML-2017-ArjevaniS #complexity #higher-order #problem: Oracle Complexity of Second-Order Methods for Finite-Sum Problems (YA, OS), pp. 205–213.
ICML-2017-ArjovskyCB #generative #network: Wasserstein Generative Adversarial Networks (MA, SC, LB), pp. 214–223.
ICML-2017-Arora0LMZ #equilibrium #generative: Generalization and Equilibrium in Generative Adversarial Nets (GANs) (SA, RG0, YL, TM, YZ), pp. 224–232.
ICML-2017-ArpitJBKBKMFCBL #network: A Closer Look at Memorization in Deep Networks (DA, SJ, NB, DK, EB, MSK, TM, AF, ACC, YB, SLJ), pp. 233–242.
ICML-2017-AsadiL #learning: An Alternative Softmax Operator for Reinforcement Learning (KA, MLL), pp. 243–252.
ICML-2017-AvronKMMVZ #approximate #bound #fourier #kernel #random #statistics: Random Fourier Features for Kernel Ridge Regression: Approximation Bounds and Statistical Guarantees (HA, MK, CM, CM, AV, AZ), pp. 253–262.
ICML-2017-AzarOM #bound #learning: Minimax Regret Bounds for Reinforcement Learning (MGA, IO, RM), pp. 263–272.
ICML-2017-BachHRR #generative #learning #modelling: Learning the Structure of Generative Models without Labeled Data (SHB, BDH, AR, CR), pp. 273–282.
ICML-2017-BachemLH0 #bound #clustering: Uniform Deviation Bounds for k-Means Clustering (OB, ML, SHH, AK0), pp. 283–291.
ICML-2017-BachemL0 #constant #distributed: Distributed and Provably Good Seedings for k-Means in Constant Rounds (OB, ML, AK0), pp. 292–300.
ICML-2017-BachmanST #algorithm #learning: Learning Algorithms for Active Learning (PB, AS, AT), pp. 301–310.
ICML-2017-BackursT #algorithm #clique #performance: Improving Viterbi is Hard: Better Runtimes Imply Faster Clique Algorithms (AB, CT), pp. 311–321.
ICML-2017-BalcanDLMZ #clustering: Differentially Private Clustering in High-Dimensional Euclidean Spaces (MFB, TD, YL, WM, HZ0), pp. 322–331.
ICML-2017-Balduzzi: Strongly-Typed Agents are Guaranteed to Interact Safely (DB), pp. 332–341.
ICML-2017-BalduzziFLLMM #problem #question #what: The Shattered Gradients Problem: If resnets are the answer, then what is the question? (DB, MF, LL, JPL, KWDM, BM), pp. 342–350.
ICML-2017-BalduzziMB #approximate #convergence #network: Neural Taylor Approximations: Convergence and Exploration in Rectifier Networks (DB, BM, TBY), pp. 351–360.
ICML-2017-BalleM #finite #learning #policy: Spectral Learning from a Single Trajectory under Finite-State Policies (BB, OAM), pp. 361–370.
ICML-2017-BalogTGW: Lost Relatives of the Gumbel Trick (MB, NT, ZG, AW), pp. 371–379.
ICML-2017-BamlerM #word: Dynamic Word Embeddings (RB, SM), pp. 380–389.
ICML-2017-BaramACM #learning: End-to-End Differentiable Adversarial Imitation Learning (NB, OA, IC, SM), pp. 390–399.
ICML-2017-BarmannPS #learning #online #optimisation: Emulating the Expert: Inverse Optimization through Online Learning (AB, SP, OS), pp. 400–410.
ICML-2017-BeckhamP #classification #probability: Unimodal Probability Distributions for Deep Ordinal Classification (CB, CJP), pp. 411–419.
ICML-2017-BegonJG: Globally Induced Forest: A Prepruning Compression Scheme (JMB, AJ, PG), pp. 420–428.
ICML-2017-BelangerYM #energy #learning #network #predict: End-to-End Learning for Structured Prediction Energy Networks (DB, BY, AM), pp. 429–439.
ICML-2017-BelilovskyKVB #learning #modelling #visual notation: Learning to Discover Sparse Graphical Models (EB, KK, GV, MBB), pp. 440–448.
ICML-2017-BellemareDM #learning: A Distributional Perspective on Reinforcement Learning (MGB, WD, RM), pp. 449–458.
ICML-2017-BelloZVL #learning: Neural Optimizer Search with Reinforcement Learning (IB, BZ, VV, QVL), pp. 459–468.
ICML-2017-BergmannJV #learning: Learning Texture Manifolds with the Periodic Spatial GAN (UB, NJ, RV), pp. 469–477.
ICML-2017-BernsteinMSSHM #learning #modelling #using #visual notation: Differentially Private Learning of Undirected Graphical Models Using Collective Graphical Models (GB, RM, TS, DS, MH, GM), pp. 478–487.
ICML-2017-BeygelzimerOZ #learning #multi #online #performance: Efficient Online Bandit Multiclass Learning with Õ(√T) Regret (AB, FO, CZ), pp. 488–497.
ICML-2017-BianB0T: Guarantees for Greedy Maximization of Non-submodular Functions with Applications (AAB, JMB, AK0, ST), pp. 498–507.
ICML-2017-BogunovicMSC #approach #clustering #robust: Robust Submodular Maximization: A Non-Uniform Partitioning Approach (IB, SM, JS, VC), pp. 508–516.
ICML-2017-BojanowskiJ #learning #predict: Unsupervised Learning by Predicting Noise (PB, AJ), pp. 517–526.
ICML-2017-BolukbasiWDS #adaptation #network #performance: Adaptive Neural Networks for Efficient Inference (TB, JW0, OD, VS), pp. 527–536.
ICML-2017-BoraJPD #generative #modelling #using: Compressed Sensing using Generative Models (AB, AJ, EP, AGD), pp. 537–546.
ICML-2017-BosnjakRNR #interpreter #programming: Programming with a Differentiable Forth Interpreter (MB, TR, JN, SR0), pp. 547–556.
ICML-2017-BotevRB #learning #optimisation: Practical Gauss-Newton Optimisation for Deep Learning (AB, HR, DB), pp. 557–565.
ICML-2017-BraunPZ #algorithm: Lazifying Conditional Gradient Algorithms (GB, SP, DZ), pp. 566–575.
ICML-2017-BravermanFLSY #clustering #data type: Clustering High Dimensional Dynamic Data Streams (VB, GF, HL, CS, LFY), pp. 576–585.
ICML-2017-BriolOCCG #kernel #on the #problem: On the Sampling Problem for Kernel Quadrature (FXB, CJO, JC, WYC, MAG), pp. 586–595.
ICML-2017-BrownS #convergence #game studies #performance: Reduced Space and Faster Convergence in Imperfect-Information Games via Pruning (NB, TS), pp. 596–604.
ICML-2017-BrutzkusG: Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs (AB, AG), pp. 605–614.
ICML-2017-BuddenMSCS #multi: Deep Tensor Convolution on Multicores (DMB, AM, SS, SRC, NS), pp. 615–624.
ICML-2017-Busa-FeketeSWM #multi #optimisation: Multi-objective Bandits: Optimizing the Generalized Gini Index (RBF, BS, PW, SM), pp. 625–634.
ICML-2017-CaiDK #performance #testing: Priv'IT: Private and Sample Efficient Identity Testing (BC, CD, GK0), pp. 635–644.
ICML-2017-CalandrielloLV #adaptation #higher-order #kernel #online #optimisation #sketching: Second-Order Kernel Online Convex Optimization with Adaptive Sketching (DC, AL, MV), pp. 645–653.
ICML-2017-CarmonDHS #quote: “Convex Until Proven Guilty”: Dimension-Free Acceleration of Gradient Descent on Non-Convex Functions (YC, JCD, OH, AS), pp. 654–663.
ICML-2017-CarriereCO #diagrams #kernel #persistent #slicing: Sliced Wasserstein Kernel for Persistence Diagrams (MC, MC, SO), pp. 664–673.
ICML-2017-ChangCCCSD #clustering #multi #nondeterminism: Multiple Clustering Views from Multiple Uncertain Experts (YC, JC, MHC, PJC, EKS, JGD), pp. 674–683.
ICML-2017-ChaudhryXG #assessment #nondeterminism: Uncertainty Assessment and False Discovery Rate Control in High-Dimensional Granger Causal Inference (AC, PX0, QG), pp. 684–693.
ICML-2017-Chaudhuri0N: Active Heteroscedastic Regression (KC, PJ0, NN), pp. 694–702.
ICML-2017-ChebotarHZSSL #learning #modelling: Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning (YC, KH, MZ, GSS, SS, SL), pp. 703–711.
ICML-2017-ChenB #estimation #modelling #robust: Robust Structured Estimation with Single-Index Models (SC, AB), pp. 712–721.
ICML-2017-ChenC0Z #adaptation #identification #multi: Adaptive Multiple-Arm Identification (JC, XC0, QZ0, YZ0), pp. 722–730.
ICML-2017-ChenF: Dueling Bandits with Weak Regret (BC, PIF), pp. 731–739.
ICML-2017-ChenGWWYY #np-hard #optimisation: Strong NP-Hardness for Sparse Optimization with Concave Penalty Functions (YC, DG, MW, ZW, YY, HY), pp. 740–747.
ICML-2017-ChenHCDLBF #learning: Learning to Learn without Gradient Descent by Gradient Descent (YC, MWH, SGC, MD, TPL, MB, NdF), pp. 748–756.
ICML-2017-ChenKB #equation #identification #linear #modelling #testing #using: Identification and Model Testing in Linear Structural Equation Models using Auxiliary Variables (BC, DK, EB), pp. 757–766.
ICML-2017-ChenLK #estimation #matrix #performance #towards: Toward Efficient and Accurate Covariance Matrix Estimation on Compressed Data (XC, MRL, IK), pp. 767–776.
ICML-2017-ChenYLZ #online #optimisation #performance #scalability: Online Partial Least Square Optimization: Dropping Convexity for Better Efficiency and Scalability (ZC, LFY, CJL, TZ), pp. 777–786.
ICML-2017-ChenZLHH #learning: Learning to Aggregate Ordinal Labels by Maximizing Separating Width (GC, SZ, DL, HH0, PAH), pp. 787–796.
ICML-2017-CherapanamjeriG #matrix #robust: Nearly Optimal Robust Matrix Completion (YC, KG, PJ0), pp. 797–805.
ICML-2017-ChierichettiG0L #algorithm #approximate #rank: Algorithms for lₚ Low-Rank Approximation (FC, SG, RK0, SL, RP, DPW), pp. 806–814.
ICML-2017-ChoB #named #network: MEC: Memory-efficient Convolution for Deep Neural Network (MC, DB), pp. 815–824.
ICML-2017-ChoiD #on the: On Relaxing Determinism in Arithmetic Circuits (AC, AD), pp. 825–833.
ICML-2017-ChouMS #learning #policy #probability #using: Improving Stochastic Policy Gradients in Continuous Control with Deep Reinforcement Learning using the Beta Distribution (PWC, DM, SAS), pp. 834–843.
ICML-2017-ChowdhuryG #kernel #multi #on the: On Kernelized Multi-armed Bandits (SRC, AG), pp. 844–853.
ICML-2017-CisseBGDU #network #robust: Parseval Networks: Improving Robustness to Adversarial Examples (MC, PB, EG, YND, NU), pp. 854–863.
ICML-2017-CongCLZ #adaptation #probability #topic: Deep Latent Dirichlet Allocation with Topic-Layer-Adaptive Stochastic Gradient Riemannian MCMC (YC, BC0, HL, MZ), pp. 864–873.
ICML-2017-CortesGKMY #adaptation #learning #named #network: AdaNet: Adaptive Structural Learning of Artificial Neural Networks (CC, XG, VK, MM, SY), pp. 874–883.
ICML-2017-CutajarBMF #process #random: Random Feature Expansions for Deep Gaussian Processes (KC, EVB, PM, MF), pp. 884–893.
ICML-2017-CuturiB #named: Soft-DTW: a Differentiable Loss Function for Time-Series (MC, MB), pp. 894–903.
ICML-2017-CzarneckiSJOVK #comprehension #interface: Understanding Synthetic Gradients and Decoupled Neural Interfaces (WMC, GS, MJ, SO, OV, KK), pp. 904–912.
ICML-2017-DaiGKHS #generative #probability: Stochastic Generative Hashing (BD, RG, SK, NH, LS), pp. 913–922.
ICML-2017-DaumeKLM: Logarithmic Time One-Against-Some (HDI, NK, JL0, PM), pp. 923–932.
ICML-2017-DauphinFAG #modelling #network: Language Modeling with Gated Convolutional Networks (YND, AF, MA, DG), pp. 933–941.
ICML-2017-DawsonHM #infinity #markov: An Infinite Hidden Markov Model With Similarity-Biased Transitions (CRD, CH, CTM), pp. 942–950.
ICML-2017-DaxbergerL #distributed #optimisation #process: Distributed Batch Gaussian Process Optimization (EAD, BKHL), pp. 951–960.
ICML-2017-DembczynskiKKN #analysis #classification #consistency #revisited: Consistency Analysis for Binary Classification Revisited (KD, WK, OK, NN), pp. 961–969.
ICML-2017-DempseyMSDGMR #named #predict: iSurvive: An Interpretable, Event-time Prediction Model for mHealth (WHD, AM, CKS, MLD, DHG, SAM, JMR), pp. 970–979.
ICML-2017-DengKLR #generative: Image-to-Markup Generation with Coarse-to-Fine Attention (YD, AK, JL, AMR), pp. 980–989.
ICML-2017-DevlinUBSMK #learning #named: RobustFill: Neural Program Learning under Noisy I/O (JD, JU, SB, RS, ArM, PK), pp. 990–998.
ICML-2017-DiakonikolasKK0 #robust: Being Robust (in High Dimensions) Can Be Practical (ID, GK0, DMK, JL0, AM, AS), pp. 999–1008.
ICML-2017-DinhBZM #monte carlo #probability: Probabilistic Path Hamiltonian Monte Carlo (VD, AB, CZ, FAMI), pp. 1009–1018.
ICML-2017-DinhPBB: Sharp Minima Can Generalize For Deep Nets (LD, RP, SB, YB), pp. 1019–1028.
ICML-2017-Domke #bound: A Divergence Bound for Hybrids of MCMC and Variational Inference and an Application to Langevin Dynamics and SGVI (JD), pp. 1029–1038.
ICML-2017-DonahueLM: Dance Dance Convolution (CD, ZCL, JJM), pp. 1039–1048.
ICML-2017-DuCLXZ #evaluation #policy #probability #reduction: Stochastic Variance Reduction Methods for Policy Evaluation (SSD, JC, LL0, LX, DZ), pp. 1049–1058.
ICML-2017-EcksteinGK #generative #using: Rule-Enhanced Penalized Regression by Column Generation using Rectangular Maximum Agreement (JE, NG, AK), pp. 1059–1067.
ICML-2017-EngelRRDNES #synthesis: Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders (JHE, CR, AR, SD, MN0, DE, KS), pp. 1068–1077.
ICML-2017-FahandarHC #ranking #statistics: Statistical Inference for Incomplete Ranking Data: The Case of Rank-Dependent Coarsening (MAF, EH, IC), pp. 1078–1087.
ICML-2017-FalahatgarOPS #ranking: Maximum Selection and Ranking under Noisy Comparisons (MF, AO, VP, ATS), pp. 1088–1096.
ICML-2017-FarajtabarYYXTK #process: Fake News Mitigation via Point Process Based Intervention (MF, JY, XY, HX, RT, EBK, SL0, LS, HZ), pp. 1097–1106.
ICML-2017-FarinaKS #behaviour #game studies: Regret Minimization in Behaviorally-Constrained Zero-Sum Games (GF, CK, TS), pp. 1107–1116.
ICML-2017-FeldmanOR #graph #network #summary: Coresets for Vector Summarization with Applications to Network Graphs (DF, SO, DR), pp. 1117–1125.
ICML-2017-FinnAL #adaptation #network #performance: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (CF, PA, SL), pp. 1126–1135.
ICML-2017-FoersterGSCS #architecture #network: Input Switched Affine Networks: An RNN Architecture Designed for Interpretability (JNF, JG, JSD, JC, DS), pp. 1136–1145.
ICML-2017-FoersterNFATKW #experience #learning #multi: Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning (JNF, NN, GF, TA, PHST, PK, SW), pp. 1146–1155.
ICML-2017-ForneyPB #online: Counterfactual Data-Fusion for Online Reinforcement Learners (AF, JP, EB), pp. 1156–1164.
ICML-2017-FranceschiDFP #optimisation: Forward and Reverse Gradient-Based Hyperparameter Optimization (LF, MD, PF, MP), pp. 1165–1173.
ICML-2017-FutomaHH #classification #detection #learning #multi #process: Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier (JF, SH, KAH), pp. 1174–1182.
ICML-2017-GalIG #image #learning: Deep Bayesian Active Learning with Image Data (YG, RI, ZG), pp. 1183–1192.
ICML-2017-GaoFC #learning #network: Local-to-Global Bayesian Network Structure Learning (TG, KPF, MC), pp. 1193–1202.
ICML-2017-GarberSS #algorithm #analysis #component #distributed #probability: Communication-efficient Algorithms for Distributed Stochastic Principal Component Analysis (DG, OS, NS), pp. 1203–1212.
ICML-2017-GauntBKT #library #source code: Differentiable Programs with Neural Libraries (ALG, MB, NK, DT), pp. 1213–1222.
ICML-2017-GautierBV #performance: Zonotope Hit-and-run for Efficient Sampling from Projection DPPs (GG, RB, MV), pp. 1223–1232.
ICML-2017-0001JZ #analysis #geometry #problem #rank: No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis (RG0, CJ, YZ), pp. 1233–1242.
ICML-2017-GehringAGYD #learning #sequence: Convolutional Sequence to Sequence Learning (JG, MA, DG, DY, YND), pp. 1243–1252.
ICML-2017-GentileLKKZE #clustering #on the: On Context-Dependent Clustering of Bandits (CG, SL, PK, AK, GZ, EE), pp. 1253–1262.
ICML-2017-GilmerSRVD #message passing #quantum: Neural Message Passing for Quantum Chemistry (JG, SSS, PFR, OV, GED), pp. 1263–1272.
ICML-2017-GoldsteinS #retrieval: Convex Phase Retrieval without Lifting via PhaseMax (TG, CS), pp. 1273–1281.
ICML-2017-GonzalezDDL #optimisation: Preferential Bayesian Optimization (JG, ZD, ACD, NDL), pp. 1282–1291.
ICML-2017-GorhamM #kernel #quality: Measuring Sample Quality with Kernels (JG, LWM), pp. 1292–1301.
ICML-2017-GraveJCGJ #approximate #performance: Efficient softmax approximation for GPUs (EG, AJ, MC, DG, HJ), pp. 1302–1310.
ICML-2017-GravesBMMK #automation #education #learning #network: Automated Curriculum Learning for Neural Networks (AG, MGB, JM, RM, KK), pp. 1311–1320.
ICML-2017-GuoPSW #network #on the: On Calibration of Modern Neural Networks (CG, GP, YS0, KQW), pp. 1321–1330.
ICML-2017-GuptaSGSPKGUV0 #named: ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices (CG, ASS, AG, HVS, BP, AK, SG, RU, MV, PJ0), pp. 1331–1340.
ICML-2017-GygliNA #network: Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs (MG, MN0, AA), pp. 1341–1351.
ICML-2017-HaarnojaTAL #energy #learning #policy: Reinforcement Learning with Deep Energy-Based Policies (TH, HT, PA, SL), pp. 1352–1361.
ICML-2017-HadjeresPN #generative #named: DeepBach: a Steerable Model for Bach Chorales Generation (GH, FP, FN), pp. 1362–1371.
ICML-2017-HallakM #consistency #evaluation #online: Consistent On-Line Off-Policy Evaluation (AH, SM), pp. 1372–1383.
ICML-2017-HanKPS #performance #process: Faster Greedy MAP Inference for Determinantal Point Processes (IH, PK, KP, JS), pp. 1384–1393.
ICML-2017-HannaTSN #behaviour #evaluation #policy: Data-Efficient Policy Evaluation Through Behavior Policy Search (JPH, PST, PS, SN), pp. 1394–1403.
ICML-2017-HarandiSH #geometry #learning #metric #reduction: Joint Dimensionality Reduction and Metric Learning: A Geometric Take (MTH, MS, RIH), pp. 1404–1413.
ICML-2017-HartfordLLT #approach #flexibility #predict: Deep IV: A Flexible Approach for Counterfactual Prediction (JSH, GL, KLB, MT), pp. 1414–1423.
ICML-2017-HassidimS #algorithm #probability #robust: Robust Guarantees of Stochastic Greedy Algorithms (AH, YS), pp. 1424–1432.
ICML-2017-HazanSZ #game studies #performance: Efficient Regret Minimization in Non-Convex Games (EH, KS, CZ), pp. 1433–1441.
ICML-2017-HeLMWSYR #kernel: Kernelized Support Tensor Machines (LH0, CTL, GM, SW, LS, PSY, ABR), pp. 1442–1451.
ICML-2017-HeckelR #collaboration #complexity #online: The Sample Complexity of Online One-Class Collaborative Filtering (RH, KR), pp. 1452–1460.
ICML-2017-HenriquesV #performance: Warped Convolutions: Efficient Invariance to Spatial Transformations (JFH, AV), pp. 1461–1469.
ICML-2017-Hernandez-Lobato #distributed #parallel #scalability: Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space (JMHL, JR, EOPK, AAG), pp. 1470–1479.
ICML-2017-HigginsPRMBPBBL #learning #named: DARLA: Improving Zero-Shot Transfer in Reinforcement Learning (IH, AP, AAR, LM, CB, AP, MB, CB, AL), pp. 1480–1490.
ICML-2017-HirayamaHK #named: SPLICE: Fully Tractable Hierarchical Extension of ICA with Pooling (JH, AH, MK), pp. 1491–1500.
ICML-2017-HoNYBHP #clustering #multi: Multilevel Clustering via Wasserstein Means (NH, XN, MY, HHB, VH, DQP), pp. 1501–1509.
ICML-2017-Hoffman #learning #markov #modelling #monte carlo: Learning Deep Latent Gaussian Models with Markov Chain Monte Carlo (MDH), pp. 1510–1519.
ICML-2017-HonerNBMG #detection #robust #trust: Minimizing Trust Leaks for Robust Sybil Detection (JH, SN, AB0, KRM, NG), pp. 1520–1528.
ICML-2017-HongHZ #algorithm #distributed #learning #named #network #optimisation #performance: Prox-PDA: The Proximal Primal-Dual Algorithm for Fast Distributed Nonconvex Optimization and Learning Over Networks (MH, DH, MMZ), pp. 1529–1538.
ICML-2017-HornakovaLA #analysis #graph #multi #optimisation: Analysis and Optimization of Graph Decompositions by Lifted Multicuts (AH, JHL, BA), pp. 1539–1548.
ICML-2017-HuL: Dissipativity Theory for Nesterov's Accelerated Method (BH, LL), pp. 1549–1557.
ICML-2017-HuMTMS #learning #self: Learning Discrete Representations via Information Maximizing Self-Augmented Training (WH, TM, ST, EM, MS), pp. 1558–1567.
ICML-2017-HuQ #memory management #network: State-Frequency Memory Recurrent Neural Networks (HH, GJQ), pp. 1568–1577.
ICML-2017-HuRC #generative #modelling #relational: Deep Generative Models for Relational Data with Side Information (CH, PR, LC), pp. 1578–1586.
ICML-2017-HuYLSX #generative #towards: Toward Controlled Generation of Text (ZH, ZY, XL, RS, EPX), pp. 1587–1596.
ICML-2017-ImaizumiH #composition: Tensor Decomposition with Smoothness (MI, KH), pp. 1597–1606.
ICML-2017-IngrahamM #modelling: Variational Inference for Sparse and Undirected Models (JI, DSM), pp. 1607–1616.
ICML-2017-JabbariJKMR #learning: Fairness in Reinforcement Learning (SJ, MJ, MJK, JM, AR0), pp. 1617–1626.
ICML-2017-JaderbergCOVGSK #interface #using: Decoupled Neural Interfaces using Synthetic Gradients (MJ, WMC, SO, OV, AG, DS, KK), pp. 1627–1635.
ICML-2017-JainMR #generative #learning #modelling #multi #scalability: Scalable Generative Models for Multi-label Learning with Missing Labels (VJ, NM, PR), pp. 1636–1644.
ICML-2017-JaquesGBHTE #generative #modelling #sequence: Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control (NJ, SG, DB, JMHL, RET, DE), pp. 1645–1654.
ICML-2017-JenattonAGS #dependence #optimisation: Bayesian Optimization with Tree-structured Dependencies (RJ, CA, JG, MWS), pp. 1655–1664.
ICML-2017-JerniteCS #classification #estimation #learning: Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimation (YJ, AC, DAS), pp. 1665–1674.
ICML-2017-JiHS #generative #image #parametricity: From Patches to Images: A Nonparametric Generative Model (GJ0, MCH, EBS), pp. 1675–1683.
ICML-2017-Jiang #estimation #set: Density Level Set Estimation on Manifolds with DBSCAN (HJ), pp. 1684–1693.
ICML-2017-Jiang17a #convergence #estimation #kernel: Uniform Convergence Rates for Kernel Density Estimation (HJ), pp. 1694–1703.
ICML-2017-JiangKALS #process #rank: Contextual Decision Processes with low Bellman rank are PAC-Learnable (NJ, AK, AA, JL0, RES), pp. 1704–1713.
ICML-2017-JiangMCSMG #performance: Efficient Nonmyopic Active Search (SJ, GM, GC, AS, BM, RG), pp. 1714–1723.
ICML-2017-Jin0NKJ #how: How to Escape Saddle Points Efficiently (CJ, RG0, PN, SMK, MIJ), pp. 1724–1732.
ICML-2017-JingSDPSLTS #network #performance: Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs (LJ, YS, TD, JP, SAS, YL, MT, MS), pp. 1733–1741.
ICML-2017-Jitkrittum0G #adaptation #independence #kernel: An Adaptive Test of Independence with Analytic Kernel Embeddings (WJ, ZS0, AG), pp. 1742–1751.
ICML-2017-JohnsonG #coordination #named: StingyCD: Safely Avoiding Wasteful Updates in Coordinate Descent (TBJ, CG), pp. 1752–1760.
ICML-2017-KakizakiFS: Differentially Private Chi-squared Test by Unit Circle Mechanism (KK, KF, JS), pp. 1761–1770.
ICML-2017-KalchbrennerOSD #network #video: Video Pixel Networks (NK, AvdO, KS, ID, OV, AG, KK), pp. 1771–1779.
ICML-2017-KaleKLP #adaptation #feature model #linear #online #performance: Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP (SK, ZSK, TL, DP), pp. 1780–1788.
ICML-2017-Kallus #clustering #personalisation #recursion #using: Recursive Partitioning for Personalization using Observational Data (NK), pp. 1789–1798.
ICML-2017-KandasamyDSP #approximate #multi #optimisation: Multi-fidelity Bayesian Optimisation with Continuous Approximations (KK, GD, JGS, BP), pp. 1799–1808.
ICML-2017-KanskySMELLDSPG #generative #network #physics: Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics (KK, TS, DAM, ME, MLG, XL, ND, SS, DSP, DG), pp. 1809–1818.
ICML-2017-KattOA #learning #monte carlo: Learning in POMDPs with Monte Carlo Tree Search (SK, FAO, CA), pp. 1819–1827.
ICML-2017-KearnsRW: Meritocratic Fairness for Cross-Population Selection (MJK, AR0, ZSW), pp. 1828–1836.
ICML-2017-KhannaEDGN #approximate #on the #optimisation #rank: On Approximation Guarantees for Greedy Low Rank Optimization (RK, ERE, AGD, JG, SNN), pp. 1837–1846.
ICML-2017-KhasanovaF #graph #invariant #learning #representation: Graph-based Isometry Invariant Representation Learning (RK, PF), pp. 1847–1856.
ICML-2017-KimCKLK #generative #learning #network: Learning to Discover Cross-Domain Relations with Generative Adversarial Networks (TK, MC, HK, JKL, JK), pp. 1857–1865.
ICML-2017-KimPKH #learning #named #network #parallel #parametricity #reduction #semantics: SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model Parallelization (JK, YP, GK, SJH), pp. 1866–1874.
ICML-2017-KocaogluDV #graph #learning: Cost-Optimal Learning of Causal Graphs (MK, AD, SV), pp. 1875–1884.
ICML-2017-KohL #black box #comprehension #predict: Understanding Black-box Predictions via Influence Functions (PWK, PL), pp. 1885–1894.
ICML-2017-KohlerL #optimisation #polynomial: Sub-sampled Cubic Regularization for Non-convex Optimization (JMK, AL), pp. 1895–1904.
ICML-2017-KolesnikovL #image #modelling: PixelCNN Models with Auxiliary Variables for Natural Image Modeling (AK, CHL), pp. 1905–1914.
ICML-2017-KrishnamurthyAH #classification #learning: Active Learning for Cost-Sensitive Classification (AK, AA, TKH, HDI, JL0), pp. 1915–1924.
ICML-2017-KucukelbirWB #modelling: Evaluating Bayesian Models with Posterior Dispersion Indices (AK, YW, DMB), pp. 1925–1934.
ICML-2017-KumarGV #internet #machine learning #ram: Resource-efficient Machine Learning in 2 KB RAM for the Internet of Things (AK, SG, MV), pp. 1935–1944.
ICML-2017-KusnerPH: Grammar Variational Autoencoder (MJK, BP, JMHL), pp. 1945–1954.
ICML-2017-LaclauRMBB #clustering: Co-clustering through Optimal Transport (CL, IR, BM, YB, VB), pp. 1955–1964.
ICML-2017-LanPZZ #lazy evaluation #probability: Conditional Accelerated Lazy Stochastic Gradient Descent (GL, SP, YZ, DZ), pp. 1965–1974.
ICML-2017-LattanziV #clustering #consistency: Consistent k-Clustering (SL, SV), pp. 1975–1984.
ICML-2017-LawUZ #clustering #learning: Deep Spectral Clustering Learning (MTL, RU, RSZ), pp. 1985–1994.
ICML-2017-LeY0L #coordination #learning #multi: Coordinated Multi-Agent Imitation Learning (HML0, YY, PC0, PL), pp. 1995–2003.
ICML-2017-LeeHGJC #graph #random: Bayesian inference on random simple graphs with power law degree distributions (JL, CH, ZG, LFJ, SC), pp. 2004–2013.
ICML-2017-LeeHPS #learning #multi: Confident Multiple Choice Learning (KL, CH, KP, JS), pp. 2014–2023.
ICML-2017-LeiJBJ #architecture #graph #kernel #sequence: Deriving Neural Architectures from Sequence and Graph Kernels (TL0, WJ, RB, TSJ), pp. 2024–2033.
ICML-2017-LeiYWDR #coordination #empirical: Doubly Greedy Primal-Dual Coordinate Descent for Sparse Empirical Risk Minimization (QL, IEHY, CYW, ISD, PR), pp. 2034–2042.
ICML-2017-LevyW #learning #source code: Learning to Align the Source Code to the Compiled Object Code (DL, LW), pp. 2043–2051.
ICML-2017-LiG #network: Dropout Inference in Bayesian Neural Networks with Alpha-divergences (YL, YG), pp. 2052–2061.
ICML-2017-LiL #correlation #matrix: Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations (YL, YL), pp. 2062–2070.
ICML-2017-LiLZ #algorithm #linear: Provably Optimal Algorithms for Generalized Linear Contextual Bandits (LL0, YL, DZ), pp. 2071–2080.
ICML-2017-LiM #nearest neighbour #performance: Fast k-Nearest Neighbour Search via Prioritized DCI (KL, JM), pp. 2081–2090.
ICML-2017-LiM17a #robust: Forest-type Regression with General Losses and Robust Forest (AHL, AM), pp. 2091–2100.
ICML-2017-LiTE #adaptation #algorithm #equation #probability: Stochastic Modified Equations and Adaptive Stochastic Gradient Algorithms (QL, CT, WE), pp. 2101–2110.
ICML-2017-LiZLV #analysis #convergence #optimisation: Convergence Analysis of Proximal Gradient with Momentum for Nonconvex Optimization (QL, YZ, YL, PKV), pp. 2111–2119.
ICML-2017-LindgrenDK: Exact MAP Inference by Avoiding Fractional Vertices (EML, AGD, ARK), pp. 2120–2129.
ICML-2017-LiporB #clustering: Leveraging Union of Subspace Structure to Improve Constrained Clustering (JL, LB), pp. 2130–2139.
ICML-2017-LiuB #exponential #product line: Zero-Inflated Exponential Family Embeddings (LPL, DMB), pp. 2140–2148.
ICML-2017-LiuDHTYSRS #education: Iterative Machine Teaching (WL, BD, AH, CT, CY0, LBS, JMR, LS), pp. 2149–2158.
ICML-2017-LiuLNT #algorithm #complexity: Algorithmic Stability and Hypothesis Complexity (TL, GL, GN, DT), pp. 2159–2167.
ICML-2017-LiuWY #multi: Analogical Inference for Multi-relational Embeddings (HL, YW, YY), pp. 2168–2178.
ICML-2017-LiuYWLM: Dual Iterative Hard Thresholding: From Non-convex Sparse Minimization to Non-smooth Concave Maximization (BL0, XTY, LW, QL0, DNM), pp. 2179–2187.
ICML-2017-LiuZLS #automation #composition #named #sequence: Gram-CTC: Automatic Unit Selection and Target Decomposition for Sequence Labelling (HL, ZZ, XL, SS), pp. 2188–2197.
ICML-2017-LivniCG #infinity #kernel #learning #network: Learning Infinite Layer Networks Without the Kernel Trick (RL, DC, AG), pp. 2198–2207.
ICML-2017-LongZ0J #adaptation #learning #network: Deep Transfer Learning with Joint Adaptation Networks (ML, HZ, JW0, MIJ), pp. 2208–2217.
ICML-2017-LouizosW #multi #network #normalisation: Multiplicative Normalizing Flows for Variational Bayesian Neural Networks (CL, MW), pp. 2218–2227.
ICML-2017-Loukas #how #matrix #question: How Close Are the Eigenvectors of the Sample and Actual Covariance Matrices? (AL), pp. 2228–2237.
ICML-2017-Luo #architecture #learning #network: Learning Deep Architectures via Generalized Whitened Neural Networks (PL0), pp. 2238–2246.
ICML-2017-LvJL #learning: Learning Gradient Descent: Better Generalization and Longer Horizons (KL, SJ, JL), pp. 2247–2255.
ICML-2017-Lyu #approximate #kernel: Spherical Structured Feature Maps for Kernel Approximation (YL), pp. 2256–2264.
ICML-2017-MaFF #markov #modelling #probability: Stochastic Gradient MCMC Methods for Hidden Markov Models (YAM, NJF, EBF), pp. 2265–2274.
ICML-2017-MaMXLD #self: Self-Paced Co-training (FM, DM, QX, ZL, XD), pp. 2275–2284.
ICML-2017-MacGlashanHLPWR #feedback #interactive #learning: Interactive Learning from Policy-Dependent Human Feedback (JM, MKH, RTL, BP, GW, DLR, MET, MLL), pp. 2285–2294.
ICML-2017-MachadoBB #framework #learning: A Laplacian Framework for Option Discovery in Reinforcement Learning (MCM, MGB, MHB), pp. 2295–2304.
ICML-2017-MairBB: Frame-based Data Factorizations (SM, AB, UB), pp. 2305–2313.
ICML-2017-MalherbeV #optimisation: Global optimization of Lipschitz functions (CM, NV), pp. 2314–2323.
ICML-2017-MaoSC #matrix #on the #symmetry: On Mixed Memberships and Symmetric Nonnegative Matrix Factorizations (XM0, PS, DC), pp. 2324–2333.
ICML-2017-MasegosaNLRSM #data type #modelling: Bayesian Models of Data Streams with Hierarchical Power Priors (ARM, TDN, HL, DRL, AS, ALM), pp. 2334–2343.
ICML-2017-MaystreG #approach #effectiveness #exclamation #learning: Just Sort It! A Simple and Effective Approach to Active Preference Learning (LM, MG), pp. 2344–2353.
ICML-2017-MaystreG17a #identification #named #network: ChoiceRank: Identifying Preferences from Node Traffic in Networks (LM, MG), pp. 2354–2362.
ICML-2017-McGillP #how #network: Deciding How to Decide: Dynamic Routing in Artificial Neural Networks (MM, PP), pp. 2363–2372.
ICML-2017-McNamaraB #bound: Risk Bounds for Transferring Representations With and Without Fine-Tuning (DM, MFB), pp. 2373–2381.
ICML-2017-MeiCGH #matrix: Nonnegative Matrix Factorization for Time Series Recovery From a Few Temporal Aggregates (JM, YdC, YG, GH), pp. 2382–2390.
ICML-2017-MeschederNG #generative #network: Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks (LMM, SN, AG), pp. 2391–2400.
ICML-2017-MhammediHRB #network #orthogonal #performance #using: Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections (ZM, ADH, AR, JB0), pp. 2401–2409.
ICML-2017-MiaoGB #topic: Discovering Discrete Latent Topics with Neural Variational Inference (YM, EG, PB), pp. 2410–2419.
ICML-2017-MillerFA #approximate: Variational Boosting: Iteratively Refining Posterior Approximations (ACM, NJF, RPA), pp. 2420–2429.
ICML-2017-MirhoseiniPLSLZ #learning #optimisation: Device Placement Optimization with Reinforcement Learning (AM, HP, QVL, BS, RL0, YZ, NK, MN0, SB, JD), pp. 2430–2439.
ICML-2017-MirrokniLVW #approximate #bound: Tight Bounds for Approximate Carathéodory and Beyond (VSM, RPL, AV, SCwW), pp. 2440–2448.
ICML-2017-MirzasoleimanK0 #summary: Deletion-Robust Submodular Maximization: Data Summarization with “the Right to be Forgotten” (BM, AK, AK0), pp. 2449–2458.
ICML-2017-MishraAM #modelling #predict: Prediction and Control with Temporal Segment Models (NM, PA, IM), pp. 2459–2468.
ICML-2017-MitliagkasM #quality: Improving Gibbs Sampler Scan Quality with DoGS (IM, LWM), pp. 2469–2477.
ICML-2017-MitrovicB0K #summary: Differentially Private Submodular Maximization: Data Summarization in Disguise (MM, MB, AK0, AK), pp. 2478–2487.
ICML-2017-MohajerSE #learning #rank: Active Learning for Top-K Rank Aggregation from Noisy Comparisons (SM, CS, AE), pp. 2488–2497.
ICML-2017-MolchanovAV #network: Variational Dropout Sparsifies Deep Neural Networks (DM, AA, DPV), pp. 2498–2507.
ICML-2017-MollaysaSK #modelling #using: Regularising Non-linear Models Using Feature Side-information (AM, PS, AK), pp. 2508–2517.
ICML-2017-MouLLJ #distributed #execution #natural language #query #symbolic computation: Coupling Distributed and Symbolic Execution for Natural Language Queries (LM, ZL, HL0, ZJ), pp. 2518–2526.
ICML-2017-MrouehSG #named: McGan: Mean and Covariance Feature Matching GAN (YM, TS, VG), pp. 2527–2535.
ICML-2017-MuellerGJ #combinator #sequence: Sequence to Better Sequence: Continuous Revision of Combinatorial Structures (JM, DKG, TSJ), pp. 2536–2544.
ICML-2017-MukkamalaH #bound: Variants of RMSProp and Adagrad with Logarithmic Regret Bounds (MCM, MH0), pp. 2545–2553.
ICML-2017-MunkhdalaiY #network: Meta Networks (TM, HY0), pp. 2554–2563.
ICML-2017-NagamineM #case study #comprehension #multi #recognition #representation #speech: Understanding the Representation and Computation of Multilayer Perceptrons: A Case Study in Speech Recognition (TN, NM), pp. 2564–2573.
ICML-2017-NamkoongSYD #adaptation #optimisation: Adaptive Sampling Probabilities for Non-Smooth Optimization (HN, AS, SY, JCD), pp. 2574–2583.
ICML-2017-NeilLDL #network: Delta Networks for Optimized Recurrent Network Computation (DN, JL, TD, SCL), pp. 2584–2593.
ICML-2017-NeiswangerX: Post-Inference Prior Swapping (WN, EPX), pp. 2594–2602.
ICML-2017-NguyenH #network: The Loss Surface of Deep and Wide Neural Networks (QN0, MH0), pp. 2603–2612.
ICML-2017-NguyenLST #machine learning #named #novel #probability #problem #recursion #using: SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient (LMN, JL, KS, MT), pp. 2613–2621.
ICML-2017-NiQWC #clustering #modelling #persistent #visual notation: Composing Tree Graphical Models with Persistent Homology Features for Clustering Mixed-Type Data (XN, NQ, YW, CC0), pp. 2622–2631.
ICML-2017-OchiaiWHH #multi #recognition #speech: Multichannel End-to-end Speech Recognition (TO, SW, TH, JRH), pp. 2632–2641.
ICML-2017-OdenaOS #classification #image #synthesis: Conditional Image Synthesis with Auxiliary Classifier GANs (AO, CO, JS), pp. 2642–2651.
ICML-2017-OglicG #kernel: Nyström Method with Kernel K-means++ Samples as Landmarks (DO, TG0), pp. 2652–2660.
ICML-2017-OhSLK #learning #multi: Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning (JO, SPS, HL, PK), pp. 2661–2670.
ICML-2017-OlivaPS #statistics: The Statistical Recurrent Unit (JBO, BP, JGS), pp. 2671–2680.
ICML-2017-OmidshafieiPAHV #distributed #learning #multi: Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability (SO, JP, CA, JPH, JV), pp. 2681–2690.
ICML-2017-OngieWNB #algebra #matrix #modelling #rank: Algebraic Variety Models for High-Rank Matrix Completion (GO, RW, RDN, LB), pp. 2691–2700.
ICML-2017-OsbandR #learning #question #why: Why is Posterior Sampling Better than Optimism for Reinforcement Learning? (IO, BVR), pp. 2701–2710.
ICML-2017-OsogamiKS #bidirectional #learning #modelling: Bidirectional Learning for Time-series Models with Hidden Units (TO, HK, TS), pp. 2711–2720.
ICML-2017-OstrovskiBOM #modelling: Count-Based Exploration with Neural Density Models (GO, MGB, AvdO, RM), pp. 2721–2730.
ICML-2017-PadSCTU #learning #taxonomy: Dictionary Learning Based on Sparse Distribution Tomography (PP, FS, LEC, PT, MU), pp. 2731–2740.
ICML-2017-PakmanGCP #probability: Stochastic Bouncy Particle Sampler (AP, DG, DEC, LP), pp. 2741–2750.
ICML-2017-PallaKG #process: A Birth-Death Process for Feature Allocation (KP, DAK, ZG), pp. 2751–2759.
ICML-2017-PanYTB #nondeterminism #predict #process: Prediction under Uncertainty in Sparse Spectrum Gaussian Processes with Applications to Filtering and Control (YP, XY, EAT, BB), pp. 2760–2768.
ICML-2017-PanahiDJB #algorithm #clustering #convergence #incremental #probability: Clustering by Sum of Norms: Stochastic Incremental Algorithm, Convergence and Cluster Recovery (AP, DPD, FDJ, CB), pp. 2769–2777.
ICML-2017-PathakAED #predict #self: Curiosity-driven Exploration by Self-supervised Prediction (DP, PA, AAE, TD), pp. 2778–2787.
ICML-2017-PengZZQ #distributed #process: Asynchronous Distributed Variational Gaussian Process for Regression (HP, SZ, XZ, YQ), pp. 2788–2797.
ICML-2017-PenningtonB #geometry #matrix #network #random: Geometry of Neural Network Loss Surfaces via Random Matrix Theory (JP, YB), pp. 2798–2806.
ICML-2017-PentinaL #learning #multi: Multi-task Learning with Labeled and Unlabeled Tasks (AP, CHL), pp. 2807–2816.
ICML-2017-PintoDSG #learning #robust: Robust Adversarial Reinforcement Learning (LP, JD, RS, AG0), pp. 2817–2826.
ICML-2017-PritzelUSBVHWB: Neural Episodic Control (AP, BU, SS, APB, OV, DH, DW, CB), pp. 2827–2836.
ICML-2017-RaffelLLWE #linear #online: Online and Linear-Time Attention by Enforcing Monotonic Alignments (CR, MTL, PJL, RJW, DE), pp. 2837–2846.
ICML-2017-RaghuPKGS #network #on the #power of: On the Expressive Power of Deep Neural Networks (MR, BP, JMK, SG, JSD), pp. 2847–2854.
ICML-2017-RaghunathanVZ #multi: Estimating the unseen from multiple populations (AR, GV, JZ), pp. 2855–2863.
ICML-2017-RahmaniA #performance #robust: Coherence Pursuit: Fast, Simple, and Robust Subspace Recovery (MR, GKA), pp. 2864–2873.
ICML-2017-RahmaniA17a #approach #clustering #problem: Innovation Pursuit: A New Approach to the Subspace Clustering Problem (MR, GKA), pp. 2874–2882.
ICML-2017-RanaL0NV #optimisation #process: High Dimensional Bayesian Optimization with Elastic Gaussian Process (SR, CL0, SG0, VN0, SV), pp. 2883–2891.
ICML-2017-RavanbakhshSP: Equivariance Through Parameter-Sharing (SR, JGS, BP), pp. 2892–2901.
ICML-2017-RealMSSSTLK #classification #evolution #image #scalability: Large-Scale Evolution of Image Classifiers (ER, SM, AS, SS, YLS, JT, QVL, AK), pp. 2902–2911.
ICML-2017-ReedOKCWCBF #estimation #parallel: Parallel Multiscale Autoregressive Density Estimation (SER, AvdO, NK, SGC, ZW0, YC, DB, NdF), pp. 2912–2921.
ICML-2017-RippelB #adaptation #image #realtime: Real-Time Adaptive Image Compression (OR, LDB), pp. 2922–2930.
ICML-2017-RiquelmeGL #estimation #learning #linear #modelling: Active Learning for Accurate Estimation of Linear Models (CR, MG, AL), pp. 2931–2939.
ICML-2017-RitterBSB #bias #case study #network: Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study (SR, DGTB, AS, MMB), pp. 2940–2949.
ICML-2017-RubinsteinA #difference #privacy #random: Pain-Free Random Differential Privacy with Sensitivity Sampling (BIPR, FA), pp. 2950–2959.
ICML-2017-Ruggieri: Enumerating Distinct Decision Trees (SR), pp. 2960–2968.
ICML-2017-RukatHTY #matrix: Bayesian Boolean Matrix Factorisation (TR, CCH, MKT, CY), pp. 2969–2978.
ICML-2017-SafranS #approximate #network #trade-off: Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networks (IS, OS), pp. 2979–2987.
ICML-2017-SaitoUH #adaptation #symmetry: Asymmetric Tri-training for Unsupervised Domain Adaptation (KS, YU, TH), pp. 2988–2997.
ICML-2017-SakaiPNS #classification: Semi-Supervised Classification Based on Classification from Positive and Unlabeled Data (TS, MCdP, GN, MS), pp. 2998–3006.
ICML-2017-SakrKS #network #precise: Analytical Guarantees on Numerical Precision of Deep Neural Networks (CS, YK0, NRS), pp. 3007–3016.
ICML-2017-SaxeER #composition #multi: Hierarchy Through Composition with Multitask LMDPs (AMS, ACE, BR), pp. 3017–3026.
ICML-2017-ScamanBBLM #algorithm #distributed #network #optimisation: Optimal Algorithms for Smooth and Strongly Convex Distributed Optimization in Networks (KS, FRB, SB, YTL, LM), pp. 3027–3036.
ICML-2017-SchlegelPCW #adaptation #kernel #online #using: Adapting Kernel Representations Online Using Submodular Maximization (MS, YP, JC, MW), pp. 3037–3046.
ICML-2017-SelsamLD #machine learning: Developing Bug-Free Machine Learning Systems With Formal Mathematics (DS, PL, DLD), pp. 3047–3056.
ICML-2017-SenSDS #identification #online: Identifying Best Interventions through Online Importance Sampling (RS, KS, AGD, SS), pp. 3057–3066.
ICML-2017-Shalev-ShwartzS #learning: Failures of Gradient-Based Deep Learning (SSS, OS, SS), pp. 3067–3075.
ICML-2017-ShalitJS #algorithm #bound: Estimating individual treatment effect: generalization bounds and algorithms (US, FDJ, DAS), pp. 3076–3085.
ICML-2017-ShamirS #feedback #learning #online #permutation: Online Learning with Local Permutations and Delayed Feedback (OS, LS), pp. 3086–3094.
ICML-2017-SharanV #algorithm #composition: Orthogonalized ALS: A Theoretically Principled Tensor Decomposition Algorithm for Practical Use (VS, GV), pp. 3095–3104.
ICML-2017-Sheffet: Differentially Private Ordinary Least Squares (OS), pp. 3105–3114.
ICML-2017-ShenL #complexity #on the: On the Iteration Complexity of Support Recovery via Hard Thresholding Pursuit (JS0, PL0), pp. 3115–3124.
ICML-2017-ShenLYM #algorithm #multi #named #optimisation: GSOS: Gauss-Seidel Operator Splitting Algorithm for Multi-Term Nonsmooth Convex Composite Optimization (LS, WL0, GY, SM), pp. 3125–3134.
ICML-2017-ShiKFHL #framework #platform: World of Bits: An Open-Domain Platform for Web-Based Agents (TS, AK, LF, JH, PL), pp. 3135–3144.
ICML-2017-ShrikumarGK #difference #learning: Learning Important Features Through Propagating Activation Differences (AS, PG, AK), pp. 3145–3153.
ICML-2017-Shrivastava #performance: Optimal Densification for Fast and Accurate Minwise Hashing (AS), pp. 3154–3163.
ICML-2017-ShuBG #estimation: Bottleneck Conditional Density Estimation (RS, HHB, MG), pp. 3164–3172.
ICML-2017-ShyamGD: Attentive Recurrent Comparators (PS, SG, AD), pp. 3173–3181.
ICML-2017-SiZKMDH: Gradient Boosted Decision Trees for High Dimensional Sparse Output (SS, HZ0, SSK, DM, ISD, CJH), pp. 3182–3190.
ICML-2017-SilverHHSGHDRRB #learning #predict: The Predictron: End-To-End Learning and Planning (DS, HvH, MH, TS, AG, TH, GDA, DPR, NCR, AB, TD), pp. 3191–3199.
ICML-2017-Simsekli #difference #equation #markov #monte carlo #probability: Fractional Langevin Monte Carlo: Exploring Levy Driven Stochastic Differential Equations for Markov Chain Monte Carlo (US), pp. 3200–3209.
ICML-2017-0005P #estimation: Nonparanormal Information Estimation (SS0, BP), pp. 3210–3219.
ICML-2017-SivakumarB: High-Dimensional Structured Quantile Regression (VS, AB), pp. 3220–3229.
ICML-2017-StaibJ #robust: Robust Budget Allocation via Continuous Submodular Functions (MS, SJ), pp. 3230–3240.
ICML-2017-StanZ0K #probability: Probabilistic Submodular Maximization in Sub-Linear Time (SS, MZ, AK0, AK), pp. 3241–3250.
ICML-2017-StichRJ #approximate #coordination: Approximate Steepest Coordinate Descent (SUS, AR, MJ), pp. 3251–3259.
ICML-2017-SuggalaYR #modelling #visual notation: Ordinal Graphical Models: A Tale of Two Approaches (ASS, EY, PR), pp. 3260–3269.
ICML-2017-SugiyamaNT #statistics: Tensor Balancing on Statistical Manifold (MS, HN, KT), pp. 3270–3279.
ICML-2017-SunDK #algorithm: Safety-Aware Algorithms for Adversarial Contextual Bandit (WS, DD, AK), pp. 3280–3288.
ICML-2017-0001N #composition #learning #modelling #scalability: Relative Fisher Information and Natural Gradient for Learning Large Modular Models (KS0, FN), pp. 3289–3298.
ICML-2017-SunRMW #learning #named: meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting (XS0, XR, SM, HW), pp. 3299–3308.
ICML-2017-SunVGBB #learning #predict: Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction (WS0, AV, GJG, BB, JAB), pp. 3309–3318.
ICML-2017-SundararajanTY #axiom #network: Axiomatic Attribution for Deep Networks (MS, AT, QY), pp. 3319–3328.
ICML-2017-SureshYKM #communication #distributed #estimation: Distributed Mean Estimation with Limited Communication (ATS, FXY, SK, HBM), pp. 3329–3337.
ICML-2017-SuzumuraNUTT #higher-order #interactive #modelling: Selective Inference for Sparse High-Order Interaction Models (SS, KN, YU, KT, IT), pp. 3338–3347.
ICML-2017-TaiebTH #probability: Coherent Probabilistic Forecasts for Hierarchical Time Series (SBT, JWT, RJH), pp. 3348–3357.
ICML-2017-TanM #learning #modelling: Partitioned Tensor Factorizations for Learning Mixed Membership Models (ZT, SM0), pp. 3358–3367.
ICML-2017-TandonLDK #distributed #learning: Gradient Coding: Avoiding Stragglers in Distributed Learning (RT, QL, AGD, NK), pp. 3368–3376.
ICML-2017-TangGD #scalability #sketching: Gradient Projection Iterative Sketch for Large-Scale Constrained Least-Squares (JT, MG, MED), pp. 3377–3386.
ICML-2017-Telgarsky #network: Neural Networks and Rational Functions (MT), pp. 3387–3393.
ICML-2017-ThiLNT #classification #probability #problem: Stochastic DCA for the Large-sum of Non-convex Functions Problem and its Application to Group Variable Selection in Classification (HALT, HML, PDN, BT), pp. 3394–3403.
ICML-2017-Tian #analysis #convergence #network: An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis (YT), pp. 3404–3413.
ICML-2017-TokuiS: Evaluating the Variance of Likelihood-Ratio Gradient Estimators (ST, IS), pp. 3414–3423.
ICML-2017-TompsonSSP #network #simulation: Accelerating Eulerian Fluid Simulation With Convolutional Networks (JT, KS, PS, KP), pp. 3424–3433.
ICML-2017-TosattoPDR: Boosted Fitted Q-Iteration (ST, MP, CD, MR), pp. 3434–3443.
ICML-2017-ToshD #learning: Diameter-Based Active Learning (CT, SD), pp. 3444–3452.
ICML-2017-TripuraneniRGT #monte carlo: Magnetic Hamiltonian Monte Carlo (NT, MR, ZG, RET), pp. 3453–3461.
ICML-2017-TrivediDWS #graph #named #reasoning: Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs (RT, HD, YW0, LS), pp. 3462–3471.
ICML-2017-TsakirisV #clustering #component: Hyperplane Clustering via Dual Principal Component Pursuit (MCT, RV), pp. 3472–3481.
ICML-2017-TuVWGJR #locality: Breaking Locality Accelerates Block Gauss-Seidel (ST, SV, ACW, AG, MIJ, BR), pp. 3482–3491.
ICML-2017-UbaruM #classification #multi #testing: Multilabel Classification with Group Testing and Codes (SU, AM), pp. 3492–3501.
ICML-2017-UmlauftH #learning #probability: Learning Stable Stochastic Nonlinear Dynamical Systems (JU, SH), pp. 3502–3510.
ICML-2017-UrschelBMR #learning #process: Learning Determinantal Point Processes with Moments and Cycles (JU, VEB, AM, PR), pp. 3511–3520.
ICML-2017-ValeraG #automation #dataset #statistics: Automatic Discovery of the Statistical Types of Variables in a Dataset (IV, ZG), pp. 3521–3529.
ICML-2017-VaswaniKWGLS #independence #learning #online: Model-Independent Online Learning for Influence Maximization (SV, BK, ZW, MG, LVSL, MS), pp. 3530–3539.
ICML-2017-VezhnevetsOSHJS #learning #network: FeUdal Networks for Hierarchical Reinforcement Learning (ASV, SO, TS, NH, MJ, DS, KK), pp. 3540–3549.
ICML-2017-Villacampa-Calvo #classification #multi #process #scalability #using: Scalable Multi-Class Gaussian Process Classification using Expectation Propagation (CVC, DHL), pp. 3550–3559.
ICML-2017-VillegasYZSLL #learning #predict: Learning to Generate Long-term Future via Hierarchical Prediction (RV, JY, YZ, SS, XL, HL), pp. 3560–3569.
ICML-2017-VorontsovTKP #dependence #learning #network #on the #orthogonal: On orthogonality and learning recurrent networks with long term dependencies (EV, CT, SK, CP), pp. 3570–3578.
ICML-2017-WalderB #estimation #performance #process: Fast Bayesian Intensity Estimation for the Permanental Process (CJW, ANB), pp. 3579–3588.
ICML-2017-WangAD #adaptation #evaluation: Optimal and Adaptive Off-policy Evaluation in Contextual Bandits (YXW, AA, MD), pp. 3589–3597.
ICML-2017-WangFHMR #capacity #locality: Capacity Releasing Diffusion for Speed and Locality (DW0, KF, MH, MWM, SR), pp. 3598–3607.
ICML-2017-WangGM #optimisation #sketching #statistics: Sketched Ridge Regression: Optimization Perspective, Statistical Perspective, and Model Averaging (SW, AG, MWM), pp. 3608–3616.
ICML-2017-WangG #estimation #robust #visual notation: Robust Gaussian Graphical Model Estimation with Arbitrary Corruption (LW, QG), pp. 3617–3626.
ICML-2017-WangJ #optimisation #performance: Max-value Entropy Search for Efficient Bayesian Optimization (ZW, SJ), pp. 3627–3635.
ICML-2017-WangKS0 #distributed #learning #performance: Efficient Distributed Learning with Sparsity (JW, MK, NS, TZ0), pp. 3636–3645.
ICML-2017-WangKB #modelling #probability #robust: Robust Probabilistic Modeling with Bayesian Data Reweighting (YW, AK, DMB), pp. 3646–3655.
ICML-2017-WangLJK #kernel #learning #optimisation: Batched High-dimensional Bayesian Optimization via Structural Kernel Learning (ZW, CL, SJ, PK), pp. 3656–3664.
ICML-2017-WangL #composition: Tensor Decomposition via Simultaneous Power Iteration (PAW, CJL), pp. 3665–3673.
ICML-2017-WangWHMZD #modelling #sequence: Sequence Modeling via Segmentations (CW, YW, PSH, AM, DZ, LD0), pp. 3674–3683.
ICML-2017-WangWTS #policy #process: Variational Policy for Guiding Point Processes (YW0, GW, EAT, LS), pp. 3684–3693.
ICML-2017-WangX #algorithm #first-order: Exploiting Strong Convexity from Data with Primal-Dual First-Order Algorithms (JW, LX), pp. 3694–3702.
ICML-2017-WangX0T: Beyond Filters: Compact Feature Map for Portable Deep Model (YW, CX0, CX0, DT), pp. 3703–3711.
ICML-2017-WangZG #framework #matrix #rank: A Unified Variance Reduction-Based Framework for Nonconvex Low-Rank Matrix Recovery (LW, XZ, QG), pp. 3712–3721.
ICML-2017-WeiSKOG #multi #process #similarity: Source-Target Similarity Modelings for Multi-Source Transfer Gaussian Process Regression (PW, RS, YK, YSO, CKG), pp. 3722–3731.
ICML-2017-WenMBY #modelling: Latent Intention Dialogue Models (THW, YM, PB, SJY), pp. 3732–3741.
ICML-2017-White #learning #specification: Unifying Task Specification in Reinforcement Learning (MW), pp. 3742–3750.
ICML-2017-WichrowskaMHCDF #scalability: Learned Optimizers that Scale and Generalize (OW, NM, MWH, SGC, MD, NdF, JSD), pp. 3751–3760.
ICML-2017-WinnerSS #integer #modelling: Exact Inference for Integer Latent-Variable Models (KW, DS, DS), pp. 3761–3770.
ICML-2017-WrigleyLY: Tensor Belief Propagation (AW, WSL, NY), pp. 3771–3779.
ICML-2017-WuZ #metric #multi #performance: A Unified View of Multi-Label Performance Measures (XZW, ZHZ), pp. 3780–3788.
ICML-2017-XiaQCBYL #learning: Dual Supervised Learning (YX, TQ, WC0, JB0, NY, TYL), pp. 3789–3798.
ICML-2017-XieDZKYZX #constraints #learning #modelling: Learning Latent Space Models with Angular Constraints (PX, YD, YZ, AK, YY, JZ, EPX), pp. 3799–3810.
ICML-2017-XieSX: Uncorrelation and Evenness: a New Diversity-Promoting Regularizer (PX, AS, EPX), pp. 3811–3820.
ICML-2017-XuLY #convergence #optimisation #performance #probability: Stochastic Convex Optimization: Faster Local Growth Implies Faster Global Convergence (YX, QL, TY), pp. 3821–3830.
ICML-2017-XuLZ #learning #process #sequence: Learning Hawkes Processes from Short Doubly-Censored Event Sequences (HX, DL, HZ), pp. 3831–3840.
ICML-2017-0002TLFYG #adaptation #distributed #optimisation: Adaptive Consensus ADMM for Distributed Optimization (ZX0, GT, HL0, MATF, XY, TG), pp. 3841–3850.
ICML-2017-YangBL #estimation #modelling: High-dimensional Non-Gaussian Single Index Models via Thresholded Score Function Estimation (ZY, KB, HL0), pp. 3851–3860.
ICML-2017-YangFSH #clustering #learning #towards: Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering (BY, XF0, NDS, MH), pp. 3861–3870.
ICML-2017-YangGKSFL #on the #set: On The Projection Operator to A Three-view Cardinality Constrained Set (HY, SG, CK, DS, RF, JL0), pp. 3871–3880.
ICML-2017-YangHSB #modelling #using: Improved Variational Autoencoders for Text Modeling using Dilated Convolutions (ZY, ZH, RS, TBK), pp. 3881–3890.
ICML-2017-YangKT #classification #network #video: Tensor-Train Recurrent Neural Networks for Video Classification (YY, DK, VT), pp. 3891–3900.
ICML-2017-YangL0 #optimisation: A Richer Theory of Convex Constrained Optimization with Reduced Projections and Improved Rates (TY, QL, LZ0), pp. 3901–3910.
ICML-2017-YangL #modelling #statistics: Sparse + Group-Sparse Dirty Models: Statistical Guarantees without Unreasonable Conditions and a Case for Non-Convexity (EY, ACL), pp. 3911–3920.
ICML-2017-YangRS #scalability: Scalable Bayesian Rule Lists (HY, CR, MS), pp. 3921–3930.
ICML-2017-YeLZ #approximate #convergence: Approximate Newton Methods and Their Local Convergence (HY, LL, ZZ), pp. 3931–3939.
ICML-2017-YeWL: A Simulated Annealing Based Inexact Oracle for Wasserstein Loss Minimization (JY, JZW, JL0), pp. 3940–3948.
ICML-2017-YenLCSLR: Latent Feature Lasso (IEHY, WCL, SEC, ASS, SDL, PR), pp. 3949–3957.
ICML-2017-YoonH #network: Combined Group and Exclusive Sparsity for Deep Neural Networks (JY, SJH), pp. 3958–3966.
ICML-2017-ZaheerAS #clustering #modelling #sequence: Latent LSTM Allocation: Joint Clustering and Non-Linear Dynamic Modeling of Sequence Data (MZ, AA, AJS), pp. 3967–3976.
ICML-2017-ZaheerKAMS #performance: Canopy Fast Sampling with Cover Trees (MZ, SK, AA, JMFM, AJS), pp. 3977–3986.
ICML-2017-ZenkePG #learning: Continual Learning Through Synaptic Intelligence (FZ, BP, SG), pp. 3987–3995.
ICML-2017-ZhangCGHC #probability: Stochastic Gradient Monomial Gamma Sampler (YZ, CC, ZG, RH, LC), pp. 3996–4005.
ICML-2017-ZhangGFCHSC #generative: Adversarial Feature Matching for Text Generation (YZ, ZG, KF, ZC, RH, DS, LC), pp. 4006–4015.
ICML-2017-ZhangHLYCHW #reduction #scalability: Scaling Up Sparse Support Vector Machines by Simultaneous Feature and Sample Reduction (WZ, BH, WL0, JY, DC, XH0, JW0), pp. 4016–4025.
ICML-2017-ZhangHTC #learning: Re-revisiting Learning on Hypergraphs: Confidence Interval and Subgradient Method (CZ, SH, ZGT, THHC), pp. 4026–4034.
ICML-2017-Zhang0KALZ #learning #linear #modelling #named #precise: ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning (HZ, JL0, KK, DA, JL0, CZ), pp. 4035–4043.
ICML-2017-ZhangLW #network: Convexified Convolutional Neural Networks (YZ0, PL, MJW), pp. 4044–4053.
ICML-2017-ZhangZZHZ #distributed #learning #network #online: Projection-free Distributed Online Learning in Networks (WZ0, PZ, WZ0, SCHH, TZ), pp. 4054–4062.
ICML-2017-ZhangZ #multi: Multi-Class Optimal Margin Distribution Machine (TZ, ZHZ), pp. 4063–4071.
ICML-2017-ZhaoDB #relational: Leveraging Node Attributes for Incomplete Relational Data (HZ, LD, WLB), pp. 4072–4081.
ICML-2017-ZhaoLW0TY #matrix #network #rank: Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank (LZ, SL, YW, ZL0, JT0, BY0), pp. 4082–4090.
ICML-2017-ZhaoSE #generative #learning #modelling: Learning Hierarchical Features from Deep Generative Models (SZ, JS, SE), pp. 4091–4099.
ICML-2017-ZhaoYKJB #architecture #learning: Learning Sleep Stages from Radio Signals: A Conditional Adversarial Architecture (MZ, SY, DK, TSJ, MTB), pp. 4100–4109.
ICML-2017-0004K #learning: Follow the Moving Leader in Deep Learning (SZ0, JTK), pp. 4110–4119.
ICML-2017-ZhengMWCYML #probability: Asynchronous Stochastic Gradient Descent with Delay Compensation (SZ, QM, TW, WC0, NY, ZM, TYL), pp. 4120–4129.
ICML-2017-0007MW #effectiveness #learning: Collect at Once, Use Effectively: Making Non-interactive Locally Private Learning Possible (KZ0, WM, LW0), pp. 4130–4139.
ICML-2017-ZhongS0BD #network: Recovery Guarantees for One-hidden-layer Neural Networks (KZ, ZS, PJ0, PLB, ISD), pp. 4140–4149.
ICML-2017-ZhouGG #adaptation #probability: Stochastic Adaptive Quasi-Newton Methods for Minimizing Expected Values (CZ, WG, DG), pp. 4150–4159.
ICML-2017-ZhouLZ #equilibrium #game studies #identification #nash #random: Identify the Nash Equilibrium in Static Games with Random Payoffs (YZ, JL, JZ0), pp. 4160–4169.
ICML-2017-ZhouZIJWS #dataset #multi #testing: When can Multi-Site Datasets be Pooled for Regression? Hypothesis Tests, l₂-consistency and Neuroscience Applications (HHZ, YZ, VKI, SCJ, GW, VS), pp. 4170–4179.
ICML-2017-ZhuWZG #algorithm #probability: High-Dimensional Variance-Reduced Stochastic Gradient Expectation-Maximization Algorithm (RZ, LW, CZ, QG), pp. 4180–4188.
ICML-2017-ZillySKS #network: Recurrent Highway Networks (JGZ, RKS, JK, JS), pp. 4189–4198.
ICML-2017-ZoghiTGKSW #learning #modelling #online #probability #rank: Online Learning to Rank in Stochastic Click Models (MZ, TT, MG, BK, CS, ZW), pp. 4199–4208.

Doina Precup, Yee Whye TehProceedings of the 34th International Conference on Machine LearningICML, 2017.

Contents (434 items)

Doina Precup, Yee Whye Teh
Proceedings of the 34th International Conference on Machine Learning
ICML, 2017.