## Andrea Pohoreckyj Danyluk, Léon Bottou, Michael L. Littman

*Proceedings of the 26th International Conference on Machine Learning*

ICML, 2009.

@proceedings{ICML-2009, address = "Montreal, Quebec, Canada", editor = "Andrea Pohoreckyj Danyluk and Léon Bottou and Michael L. Littman", isbn = "978-1-60558-516-1", publisher = "{ACM}", series = "{ACM International Conference Proceeding Series}", title = "{Proceedings of the 26th International Conference on Machine Learning}", volume = 382, year = 2009, }

### Contents (170 items)

- ICML-2009-AdamsG #learning #named #parametricity
- Archipelago: nonparametric Bayesian semi-supervised learning (RPA, ZG), pp. 1–8.
- ICML-2009-Cortes #kernel #learning #performance #question
- Invited talk: Can learning kernels help performance? (CC), p. 1.
- ICML-2009-Freund #game studies #learning #online
- Invited talk: Drifting games, boosting and online learning (YF), p. 2.
- ICML-2009-AdamsMM #parametricity #process
- Tractable nonparametric Bayesian inference in Poisson processes with Gaussian process intensities (RPA, IM, DJCM), pp. 9–16.
- ICML-2009-BeygelzimerLZ #machine learning #reduction #summary #tutorial
- Tutorial summary: Reductions in machine learning (AB, JL, BZ), p. 12.
- ICML-2009-Even-DarM #convergence #summary #tutorial
- Tutorial summary: Convergence of natural dynamics to equilibria (EED, VSM), p. 13.
- ICML-2009-TrespY #dependence #learning #summary #tutorial
- Tutorial summary: Learning with dependencies between several response variables (VT, KY), p. 14.
- ICML-2009-WarmuthV #optimisation #overview #perspective #summary #tutorial
- Tutorial summary: Survey of boosting from an optimization perspective (MKW, SVNV), p. 15.
- ICML-2009-Niv #learning #summary #tutorial
- Tutorial summary: The neuroscience of reinforcement learning (YN), p. 16.
- ICML-2009-AiolliMS #kernel
- Route kernels for trees (FA, GDSM, AS), pp. 17–24.
- ICML-2009-BennettBC #information retrieval #machine learning #summary #tutorial
- Tutorial summary: Machine learning in IR: recent successes and new opportunities (PNB, MB, KCT), p. 17.
- ICML-2009-DasguptaL #learning #summary #tutorial
- Tutorial summary: Active learning (SD, JL), p. 18.
- ICML-2009-Leskovec #ml #network #scalability #social #summary #tutorial
- Tutorial summary: Large social and information networks: opportunities for ML (JL), p. 19.
- ICML-2009-Smith #natural language #predict #summary #tutorial
- Tutorial summary: Structured prediction for natural language processing (NAS), p. 20.
- ICML-2009-AndrzejewskiZC #modelling #topic
- Incorporating domain knowledge into topic modeling via Dirichlet Forest priors (DA, XZ, MC), pp. 25–32.
- ICML-2009-BaillyDR #analysis #component #grammar inference #problem
- Grammatical inference as a principal component analysis problem (RB, FD, LR), pp. 33–40.
- ICML-2009-BengioLCW #education #learning
- Curriculum learning (YB, JL, RC, JW), pp. 41–48.
- ICML-2009-BeygelzimerDL #learning
- Importance weighted active learning (AB, SD, JL), pp. 49–56.
- ICML-2009-BouchardZ
- Split variational inference (GB, OZ), pp. 57–64.
- ICML-2009-BoulariasC #policy #predict
- Predictive representations for policy gradient in POMDPs (AB, BCd), pp. 65–72.
- ICML-2009-BoutilierRV #elicitation #interactive #online #optimisation
- Online feature elicitation in interactive optimization (CB, KR, PV), pp. 73–80.
- ICML-2009-BuhlerH #clustering #graph
- Spectral clustering based on the graph p-Laplacian (TB, MH), pp. 81–88.
- ICML-2009-BurlW #learning
- Active learning for directed exploration of complex systems (MCB, EW), pp. 89–96.
- ICML-2009-BusettoOB
- Optimized expected information gain for nonlinear dynamical systems (AGB, CSO, JMB), pp. 97–104.
- ICML-2009-CaiWH #consistency #data analysis #probability
- Probabilistic dyadic data analysis with local and global consistency (DC, XW, XH), pp. 105–112.
- ICML-2009-CamposZJ #constraints #learning #network #using
- Structure learning of Bayesian networks using constraints (CPdC, ZZ, QJ), pp. 113–120.
- ICML-2009-Cesa-BianchiGO #bound #classification #robust
- Robust bounds for classification via selective sampling (NCB, CG, FO), pp. 121–128.
- ICML-2009-ChaudhuriKLS #analysis #canonical #clustering #correlation #multi
- Multi-view clustering via canonical correlation analysis (KC, SMK, KL, KS), pp. 129–136.
- ICML-2009-ChenTLY #learning #multi
- A convex formulation for learning shared structures from multiple tasks (JC, LT, JL, JY), pp. 137–144.
- ICML-2009-ChenGR #kernel #learning
- Learning kernels from indefinite similarities (YC, MRG, BR), pp. 145–152.
- ICML-2009-ChengSS #markov #matrix #modelling
- Matrix updates for perceptron training of continuous density hidden Markov models (CCC, FS, LKS), pp. 153–160.
- ICML-2009-ChengHH #learning #ranking
- Decision tree and instance-based learning for label ranking (WC, JCH, EH), pp. 161–168.
- ICML-2009-ChoS #analysis #learning #modelling
- Learning dictionaries of stable autoregressive models for audio scene analysis (YC, LKS), pp. 169–176.
- ICML-2009-ChoiCW #markov #modelling #multi
- Exploiting sparse Markov and covariance structure in multiresolution models (MJC, VC, ASW), pp. 177–184.
- ICML-2009-ClemenconV #estimation #parametricity
- Nonparametric estimation of the precision-recall curve (SC, NV), pp. 185–192.
- ICML-2009-DaiJXYY #framework #learning #named
- EigenTransfer: a unified framework for transfer learning (WD, OJ, GRX, QY, YY), pp. 193–200.
- ICML-2009-DaitchKS #graph
- Fitting a graph to vector data (SID, JAK, DAS), pp. 201–208.
- ICML-2009-Daume #predict #search-based
- Unsupervised search-based structured prediction (HDI), pp. 209–216.
- ICML-2009-DavisD #higher-order #logic #markov
- Deep transfer via second-order Markov logic (JD, PMD), pp. 217–224.
- ICML-2009-DeisenrothHH #process
- Analytic moment-based Gaussian process filtering (MPD, MFH, UDH), pp. 225–232.
- ICML-2009-DekelS #education
- Good learners for evil teachers (OD, OS), pp. 233–240.
- ICML-2009-DeodharGGCD #clustering #framework #scalability #semistructured data
- A scalable framework for discovering coherent co-clusters in noisy data (MD, GG, JG, HC, ISD), pp. 241–248.
- ICML-2009-DiukLL #adaptation #feature model #learning #problem
- The adaptive k-meteorologists problem and its application to structure learning and feature selection in reinforcement learning (CD, LL, BRL), pp. 249–256.
- ICML-2009-DoLF #learning #online
- Proximal regularization for online and batch learning (CBD, QVL, CSF), pp. 257–264.
- ICML-2009-DoA #markov #modelling #scalability
- Large margin training for hidden Markov models with partially observed states (TMTD, TA), pp. 265–272.
- ICML-2009-Doshi-VelezG #process
- Accelerated sampling for the Indian Buffet Process (FDV, ZG), pp. 273–280.
- ICML-2009-DoyleE #modelling #topic
- Accounting for burstiness in topic models (GD, CE), pp. 281–288.
- ICML-2009-DuanTXC #adaptation #classification #multi
- Domain adaptation from multiple sources via auxiliary classifiers (LD, IWT, DX, TSC), pp. 289–296.
- ICML-2009-DuchiS
- Boosting with structural sparsity (JCD, YS), pp. 297–304.
- ICML-2009-FarhangfarGS #image #learning
- Learning to segment from a few well-selected training images (AF, RG, CS), pp. 305–312.
- ICML-2009-FloresGMP
- GAODE and HAODE: two proposals based on AODE to deal with continuous variables (MJF, JAG, AMM, JMP), pp. 313–320.
- ICML-2009-FooDN #algorithm #learning #multi
- A majorization-minimization algorithm for (multiple) hyperparameter learning (CSF, CBD, AYN), pp. 321–328.
- ICML-2009-FuSX #evolution #network
- Dynamic mixed membership blockmodel for evolving networks (WF, LS, EPX), pp. 329–336.
- ICML-2009-GargK #algorithm #strict
- Gradient descent with sparsification: an iterative algorithm for sparse recovery with restricted isometry property (RG, RK), pp. 337–344.
- ICML-2009-GarnettOR #predict
- Sequential Bayesian prediction in the presence of changepoints (RG, MAO, SJR), pp. 345–352.
- ICML-2009-GermainLLM #classification #learning #linear
- PAC-Bayesian learning of linear classifiers (PG, AL, FL, MM), pp. 353–360.
- ICML-2009-GiesekePK #clustering #performance
- Fast evolutionary maximum margin clustering (FG, TP, OK), pp. 361–368.
- ICML-2009-GomesK #dynamic analysis #multi
- Dynamic analysis of multiagent Q-learning with ε-greedy exploration (ERG, RK), pp. 369–376.
- ICML-2009-GuiverS #modelling #ranking
- Bayesian inference for Plackett-Luce ranking models (JG, ES), pp. 377–384.
- ICML-2009-HaiderS #clustering #detection #email
- Bayesian clustering for email campaign detection (PH, TS), pp. 385–392.
- ICML-2009-HazanS #algorithm #learning #performance
- Efficient learning algorithms for changing environments (EH, CS), pp. 393–400.
- ICML-2009-Heidrich-MeisnerI #policy
- Hoeffding and Bernstein races for selecting policies in evolutionary direct policy search (VHM, CI), pp. 401–408.
- ICML-2009-HelleputteD #feature model #linear #modelling
- Partially supervised feature selection with regularized linear models (TH, PD), pp. 409–416.
- ICML-2009-HuangZM #learning
- Learning with structured sparsity (JH, TZ, DNM), pp. 417–424.
- ICML-2009-HuangS #learning #linear #sequence
- Learning linear dynamical systems without sequence information (TKH, JGS), pp. 425–432.
- ICML-2009-JacobOV #graph
- Group lasso with overlap and graph lasso (LJ, GO, JPV), pp. 433–440.
- ICML-2009-JebaraWC #graph #learning
- Graph construction and b-matching for semi-supervised learning (TJ, JW, SFC), pp. 441–448.
- ICML-2009-JetchevT #learning #predict
- Trajectory prediction: learning to map situations to robot trajectories (NJ, MT), pp. 449–456.
- ICML-2009-JiY
- An accelerated gradient method for trace norm minimization (SJ, JY), pp. 457–464.
- ICML-2009-JohnsonCC #representation
- Orbit-product representation and correction of Gaussian belief propagation (JKJ, VYC, MC), pp. 473–480.
- ICML-2009-KamisettyL #approach #assessment #quality
- A Bayesian approach to protein model quality assessment (HK, CJL), pp. 481–488.
- ICML-2009-KarampatziakisK #learning #predict
- Learning prediction suffix trees with Winnow (NK, DK), pp. 489–496.
- ICML-2009-KeglB #classification
- Boosting products of base classifiers (BK, RBF), pp. 497–504.
- ICML-2009-KokD #learning #logic #markov #network
- Learning Markov logic network structure via hypergraph lifting (SK, PMD), pp. 505–512.
- ICML-2009-KolterN #polynomial
- Near-Bayesian exploration in polynomial time (JZK, AYN), pp. 513–520.
- ICML-2009-KolterN09a #difference #feature model #learning
- Regularization and feature selection in least-squares temporal difference learning (JZK, AYN), pp. 521–528.
- ICML-2009-KondorSB
- The graphlet spectrum (RK, NS, KMB), pp. 529–536.
- ICML-2009-KotlowskiS #constraints #learning
- Rule learning with monotonicity constraints (WK, RS), pp. 537–544.
- ICML-2009-KowalskiSR #kernel #learning #multi
- Multiple indefinite kernel learning with mixed norm regularization (MK, MS, LR), pp. 545–552.
- ICML-2009-KumarMT #approximate #composition #on the
- On sampling-based approximate spectral decomposition (SK, MM, AT), pp. 553–560.
- ICML-2009-KunegisL #graph transformation #learning #predict
- Learning spectral graph transformations for link prediction (JK, AL), pp. 561–568.
- ICML-2009-KuzelkaZ #relational
- Block-wise construction of acyclic relational features with monotone irreducibility and relevancy properties (OK, FZ), pp. 569–576.
- ICML-2009-LanLML #algorithm #analysis #ranking
- Generalization analysis of listwise learning-to-rank algorithms (YL, TYL, ZM, HL), pp. 577–584.
- ICML-2009-LangT #approximate #probability #relational
- Approximate inference for planning in stochastic relational worlds (TL, MT), pp. 585–592.
- ICML-2009-LangfordSZ #learning #modelling
- Learning nonlinear dynamic models (JL, RS, TZ), pp. 593–600.
- ICML-2009-LawrenceU #matrix #process
- Non-linear matrix factorization with Gaussian processes (NDL, RU), pp. 601–608.
- ICML-2009-LeeGRN #learning #network #scalability
- Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations (HL, RBG, RR, AYN), pp. 609–616.
- ICML-2009-LiYX #collaboration #generative #learning
- Transfer learning for collaborative filtering via a rating-matrix generative model (BL, QY, XX), pp. 617–624.
- ICML-2009-Li #adaptation #classification #multi #named
- ABC-boost: adaptive base class boost for multi-class classification (PL0), pp. 625–632.
- ICML-2009-LiKZ #learning #using
- Semi-supervised learning using label mean (YFL, JTK, ZHZ), pp. 633–640.
- ICML-2009-LiangJK #exponential #learning #metric #product line
- Learning from measurements in exponential families (PL, MIJ, DK), pp. 641–648.
- ICML-2009-LiuPZ #coordination #multi #semantics
- Blockwise coordinate descent procedures for the multi-task lasso, with applications to neural semantic basis discovery (HL, MP, JZ), pp. 649–656.
- ICML-2009-LiuY #linear #performance
- Efficient Euclidean projections in linear time (JL, JY), pp. 657–664.
- ICML-2009-LiuNG #community #modelling #topic
- Topic-link LDA: joint models of topic and author community (YL, ANM, WG), pp. 665–672.
- ICML-2009-LuJD #geometry #learning #metric
- Geometry-aware metric learning (ZL, PJ, ISD), pp. 673–680.
- ICML-2009-MaSSV #identification #learning #online #scalability
- Identifying suspicious URLs: an application of large-scale online learning (JM, LKS, SS, GMV), pp. 681–688.
- ICML-2009-MairalBPS #learning #online #taxonomy
- Online dictionary learning for sparse coding (JM, FRB, JP, GS), pp. 689–696.
- ICML-2009-Makino #network #predict #representation
- Proto-predictive representation of states with simple recurrent temporal-difference networks (TM), pp. 697–704.
- ICML-2009-MarlinM #modelling #visual notation
- Sparse Gaussian graphical models with unknown block structure (BMM, KPM), pp. 705–712.
- ICML-2009-MartinsSX #approximate #natural language #parsing
- Polyhedral outer approximations with application to natural language parsing (AFTM, NAS, EPX), pp. 713–720.
- ICML-2009-McFeeL #kernel #multi #partial order
- Partial order embedding with multiple kernels (BM, GRGL), pp. 721–728.
- ICML-2009-MesmayRVP #graph #library #optimisation #performance
- Bandit-based optimization on graphs with application to library performance tuning (FdM, AR, YV, MP), pp. 729–736.
- ICML-2009-MobahiCW #learning #video
- Deep learning from temporal coherence in video (HM, RC, JW), pp. 737–744.
- ICML-2009-MooijJPS #dependence #modelling
- Regression by dependence minimization and its application to causal inference in additive noise models (JMM, DJ, JP, BS), pp. 745–752.
- ICML-2009-NeumannMP #learning
- Learning complex motions by sequencing simpler motion templates (GN, WM, JP), pp. 753–760.
- ICML-2009-NickischS #linear #modelling #scalability
- Convex variational Bayesian inference for large scale generalized linear models (HN, MWS), pp. 761–768.
- ICML-2009-NowozinJ #clustering #graph #learning #linear #programming
- Solution stability in linear programming relaxations: graph partitioning and unsupervised learning (SN, SJ), pp. 769–776.
- ICML-2009-PaisleyC #analysis #parametricity #process
- Nonparametric factor analysis with beta process priors (JWP, LC), pp. 777–784.
- ICML-2009-PanT #modelling
- Unsupervised hierarchical modeling of locomotion styles (WP, LT), pp. 785–792.
- ICML-2009-PazisL #learning #policy
- Binary action search for learning continuous-action control policies (JP, MGL), pp. 793–800.
- ICML-2009-PetersJGS #detection
- Detecting the direction of causal time series (JP, DJ, AG, BS), pp. 801–808.
- ICML-2009-PetrikZ #approximate #constraints #linear #source code
- Constraint relaxation in approximate linear programs (MP, SZ), pp. 809–816.
- ICML-2009-PlathTN #classification #image #multi #random #segmentation #using
- Multi-class image segmentation using conditional random fields and global classification (NP, MT, SN), pp. 817–824.
- ICML-2009-PoczosASGS #exclamation #learning
- Learning when to stop thinking and do something! (BP, YAY, CS, RG, NRS), pp. 825–832.
- ICML-2009-PutthividhyaAN #independence #modelling #topic
- Independent factor topic models (DP, HTA, SSN), pp. 833–840.
- ICML-2009-QiTZCZ #learning #metric #performance
- An efficient sparse metric learning in high-dimensional space via l1-penalized log-determinant regularization (GJQ, JT, ZJZ, TSC, HJZ), pp. 841–848.
- ICML-2009-QianJZHW #higher-order #random #sequence
- Sparse higher order conditional random fields for improved sequence labeling (XQ, XJ, QZ, XH, LW), pp. 849–856.
- ICML-2009-QuattoniCCD #infinity #performance
- An efficient projection for l1,infinity regularization (AQ, XC, MC, TD), pp. 857–864.
- ICML-2009-RadovanovicNI #nearest neighbour
- Nearest neighbors in high-dimensional data: the emergence and influence of hubs (MR, AN, MI), pp. 865–872.
- ICML-2009-RainaMN #learning #scalability #using
- Large-scale deep unsupervised learning using graphics processors (RR, AM, AYN), pp. 873–880.
- ICML-2009-RamanFWDR
- The Bayesian group-Lasso for analyzing contingency tables (SR, TJF, PJW, ED, VR), pp. 881–888.
- ICML-2009-RaykarYZJFVBM #learning #multi #trust
- Supervised learning from multiple experts: whom to trust when everyone lies a bit (VCR, SY, LHZ, AKJ, CF, GHV, LB, LM), pp. 889–896.
- ICML-2009-ReidW #bound
- Surrogate regret bounds for proper losses (MDR, RCW), pp. 897–904.
- ICML-2009-RoyLW #consistency #learning #modelling #probability #visual notation
- Learning structurally consistent undirected probabilistic graphical models (SR, TL, MWW), pp. 905–912.
- ICML-2009-Rueping #ranking
- Ranking interesting subgroups (SR), pp. 913–920.
- ICML-2009-Schmidt #process #using
- Function factorization using warped Gaussian processes (MNS), pp. 921–928.
- ICML-2009-Shalev-ShwartzT #probability
- Stochastic methods for l1 regularized loss minimization (SSS, AT), pp. 929–936.
- ICML-2009-ShawJ
- Structure preserving embedding (BS, TJ), pp. 937–944.
- ICML-2009-SilverT #monte carlo #simulation
- Monte-Carlo simulation balancing (DS, GT), pp. 945–952.
- ICML-2009-SindhwaniML #design #nondeterminism
- Uncertainty sampling and transductive experimental design for active dual supervision (VS, PM, RDL), pp. 953–960.
- ICML-2009-SongHSF
- Hilbert space embeddings of conditional distributions with applications to dynamical systems (LS, JH, AJS, KF), pp. 961–968.
- ICML-2009-StreichFBB #clustering #multi
- Multi-assignment clustering for Boolean data (APS, MF, DAB, JMB), pp. 969–976.
- ICML-2009-SunJY #machine learning #problem
- A least squares formulation for a class of generalized eigenvalue problems in machine learning (LS, SJ, JY), pp. 977–984.
- ICML-2009-Sutskever #analysis
- A simpler unified analysis of budget perceptrons (IS), pp. 985–992.
- ICML-2009-SuttonMPBSSW #approximate #learning #linear #performance
- Fast gradient-descent methods for temporal-difference learning with linear function approximation (RSS, HRM, DP, SB, DS, CS, EW), pp. 993–1000.
- ICML-2009-SzitaL #learning #polynomial
- Optimistic initialization and greediness lead to polynomial time learning in factored MDPs (IS, AL), pp. 1001–1008.
- ICML-2009-SzlamS
- Discriminative k-metrics (AS, GS), pp. 1009–1016.
- ICML-2009-TaylorP #approximate #kernel #learning
- Kernelized value function approximation for reinforcement learning (GT, RP), pp. 1017–1024.
- ICML-2009-TaylorH #modelling #strict
- Factored conditional restricted Boltzmann Machines for modeling motion style (GWT, GEH), pp. 1025–1032.
- ICML-2009-TielemanH #performance #persistent #using
- Using fast weights to improve persistent contrastive divergence (TT, GEH), pp. 1033–1040.
- ICML-2009-Tillman #distributed #independence #learning
- Structure learning with independent non-identically distributed data (RET), pp. 1041–1048.
- ICML-2009-Toussaint #approximate #optimisation #using
- Robot trajectory optimization using approximate inference (MT), pp. 1049–1056.
- ICML-2009-UsunierBG #classification #order #ranking
- Ranking with ordered weighted pairwise classification (NU, DB, PG), pp. 1057–1064.
- ICML-2009-VarmaB #kernel #learning #multi #performance
- More generality in efficient multiple kernel learning (MV, BRB), pp. 1065–1072.
- ICML-2009-NguyenEB #clustering #comparison #metric #question
- Information theoretic measures for clusterings comparison: is a correction for chance necessary? (XVN, JE, JB), pp. 1073–1080.
- ICML-2009-VlassisT #learning
- Model-free reinforcement learning as mixture learning (NV, MT), pp. 1081–1088.
- ICML-2009-VolkovsZ #learning #named #ranking
- BoltzRank: learning to maximize expected ranking gain (MV, RSZ), pp. 1089–1096.
- ICML-2009-WagstaffB #evaluation
- K-means in space: a radiation sensitivity evaluation (KLW, BJB), pp. 1097–1104.
- ICML-2009-WallachMSM #evaluation #modelling #topic
- Evaluation methods for topic models (HMW, IM, RS, DMM), pp. 1105–1112.
- ICML-2009-WeinbergerDLSA #learning #multi #scalability
- Feature hashing for large scale multitask learning (KQW, AD, JL, AJS, JA), pp. 1113–1120.
- ICML-2009-Welling
- Herding dynamical weights to learn (MW), pp. 1121–1128.
- ICML-2009-WoodAGJT #probability #sequence
- A stochastic memoizer for sequence data (FW, CA, JG, LJ, YWT), pp. 1129–1136.
- ICML-2009-XuWS #learning #predict
- Optimal reverse prediction: a unified perspective on supervised, unsupervised and semi-supervised learning (LX, MW, DS), pp. 1137–1144.
- ICML-2009-XuJYLK #feature model
- Non-monotonic feature selection (ZX, RJ, JY, MRL, IK), pp. 1145–1152.
- ICML-2009-YangJY #learning #online
- Online learning by ellipsoid method (LY, RJ, JY), pp. 1153–1160.
- ICML-2009-YiWSS #probability #using
- Stochastic search using the natural gradient (YS, DW, TS, JS), pp. 1161–1168.
- ICML-2009-YuJ #learning
- Learning structural SVMs with latent variables (CNJY, TJ), pp. 1169–1176.
- ICML-2009-YuM #problem
- Piecewise-stationary bandit problems with side observations (JYY, SM), pp. 1177–1184.
- ICML-2009-YuLZG #collaboration #parametricity #predict #random #scalability #using
- Large-scale collaborative prediction using a nonparametric random effects model (KY, JDL, SZ, YG), pp. 1185–1192.
- ICML-2009-YuanH #feature model #learning #robust
- Robust feature extraction via information theoretic learning (XY, BGH), pp. 1193–1200.
- ICML-2009-YueJ #information retrieval #optimisation #problem
- Interactively optimizing information retrieval systems as a dueling bandits problem (YY, TJ), pp. 1201–1208.
- ICML-2009-YuilleZ #composition #learning
- Compositional noisy-logical learning (ALY, SZ), pp. 1209–1216.
- ICML-2009-ZangZMI
- Discovering options from example trajectories (PZ, PZ, DM, CLIJ), pp. 1217–1224.
- ICML-2009-ZhanLLZ #learning #metric #using
- Learning instance specific distances using metric propagation (DCZ, ML, YFL, ZHZ), pp. 1225–1232.
- ICML-2009-ZhangKP #learning #prototype #scalability
- Prototype vector machine for large scale semi-supervised learning (KZ, JTK, BP), pp. 1233–1240.
- ICML-2009-ZhangSFD #learning
- Learning non-redundant codebooks for classifying complex objects (WZ, AS, XF, TGD), pp. 1241–1248.
- ICML-2009-ZhouSL #learning #multi
- Multi-instance learning by treating instances as non-I.I.D. samples (ZHZ, YYS, YFL), pp. 1249–1256.
- ICML-2009-ZhuAX #classification #modelling #named #topic
- MedLDA: maximum margin supervised topic models for regression and classification (JZ, AA, EPX), pp. 1257–1264.
- ICML-2009-ZhuX #markov #network #on the
- On primal and dual sparsity of Markov networks (JZ, EPX), pp. 1265–1272.
- ICML-2009-ZhuangTH #kernel #learning #named #parametricity
- SimpleNPKL: simple non-parametric kernel learning (JZ, IWT, SCHH), pp. 1273–1280.

66 ×#learning

19 ×#modelling

16 ×#multi

10 ×#performance

10 ×#predict

10 ×#scalability

10 ×#using

9 ×#summary

9 ×#tutorial

8 ×#classification

19 ×#modelling

16 ×#multi

10 ×#performance

10 ×#predict

10 ×#scalability

10 ×#using

9 ×#summary

9 ×#tutorial

8 ×#classification