Monday, June 17, 8:30 to 10:00
Keynote Speaker Carlos Guestrin
Monday, June 17, 10:30 to 12:10
Track A: Deep Learning
853, On autoencoder scoring,
Hanna Kamyshanska*, Goethe-Universitaet Frankfurt; Roland Memisevic, University of Montreal
1124, On the difficulty of training Recurrent Neural Networks,
Razvan Pascanu*, Universite de Montreal; Tomas Mikolov, Brno University of Technology; Yoshua Bengio,
1125, Maxout Networks,
Ian Goodfellow*, University of Montreal; David Warde-Farley, University of Montreal; Mehdi Mirza, University of Montreal; Aaron Courville, University of Montreal; Yoshua Bengio,
576, Collaborative hyperparameter tuning,
Rémi Bardenet, Oxford University; Mátyás Brendel; Balazs Kegl*, CNRS / University Paris-Sud; Michele Sebag
abstract/pdf/supplementary
Spotlight Presentations:
136, Learning mid-level representations of objects by harnessing the aperture problem,
Roland Memisevic*, University of Montreal; Georgios Exarchakis, University of Frankfurt
274, Approximation properties of DBNs with binary hidden units and real-valued visible units,
Oswin Krause, University of Copenhagen; Asja Fischer, INI, Ruhr-University Bochum; Tobias Glasmachers, Ruhr-University Bochum; Christian Igel*, Copenhagen University
abstract/pdf
375, Better Mixing via Deep Representations,
Yoshua Bengio* ; Gregoire Mesnil, U. Montreal; Yann Dauphin, University of Montreal; Salah Rifai, University of Montreal
abstract/pdf
532, Fast dropout training,
Sida Wang*, Stanford University; Christopher Manning, Stanford
abstract/pdf
Monday, June 17, 10:30 to 12:10
Track B: Compressed Sensing
210, Feature Selection in High-Dimensional Classification,
Mladen Kolar*, Carnegie Mellon University; Han Liu, Princeton University
abstract/pdf
105, Markov Network Estimation From Multi-attribute Data,
Mladen Kolar*, Carnegie Mellon University; Han Liu, Princeton University; Eric Xing, CMU
875, Exact Rule Learning via Boolean Compressed Sensing,
Dmitry Malioutov, IBM T J Watson Research Center; Kush Varshney*, IBM Thomas J. Watson Research Center
118, Sparse Recovery under Linear Transformation,
Ji Liu*, University of Wisconsin-Madison; Lei Yuan, Arizona State University; Jieping Ye, Arizona Sate University
246, Noisy and Missing Data Regression: Distribution-Oblivious Support Recovery,
Yudong Chen*, University of Texas at Austin; Constantine Caramanis,
abstract/pdf/supplementary
Monday, June 17, 10:30 to 12:10
Track C: Reinforcement Learning
1149, Learning Policies for Contextual Submodular Prediction,
Stephane Ross*; Jiaji Zhou; Yisong Yue, Carnegie Mellon University; Debadeepta Dey; Drew Bagnell, Carnegie Mellon University
412, Learning an Internal Dynamics Model from Control Demonstration,
Matthew Golub*, Carnegie Mellon University; Steven Chase, Carnegie Mellon University; Byron Yu, Carnegie Mellon University
abstract/pdf
423, Safe Policy Iteration,
Matteo Pirotta, Politecnico di Milano; Marcello Restelli*, Politecnico di Milano; Alessio Pecorino, Politecnico di Milano; Daniele Calandriello, Politecnico di Milano
755, Temporal Difference Methods for the Variance of the Reward To Go,
Aviv Tamar*, Technion; Dotan Di Castro, Technion; Shie Mannor, Technion
Spotlight Presentations:
465, Value Iteration with incremental representation learning for continuous POMDPs,
Sebastian Brechtel*, Karlsruhe Inst. of Technology; Tobias Gindele, KIT; R diger Dillmann, KIT
39, The Sample-Complexity of General Reinforcement Learning,
Tor Lattimore*, Australian National University; Marcus Hutter, Australian National University; Peter Sunehag, Australian National University
338, Online Feature Selection for Model-based Reinforcement Learning,
Trung Nguyen*, NUS; Zhuoru Li, NUS; Tomi Silander, National University of Singapore; Tze Yun Leong, NUS
abstract/pdf/supplementary
1073, Bayesian Learning of Recursively Factored Environments,
Marc Bellemare*, University of Alberta; Joel Veness, University of Alberta; Michael Bowling, University of Alberta
Monday, June 17, 10:30 to 12:10
Track D: Social Networks
1062, Copy or Coincidence? A Model for Detecting Social Influence and Duplication Events,
Lisa Friedland*, UMass Amherst; David Jensen; Michael Lavine, UMass Amherst
475, Mixture of Mutually Exciting Processes for Viral Diffusion,
Shuang-Hong Yang*, Georgia Tech; Hongyuan Zha, Computational Science and Engineering, Georgia Tech
abstract/pdf/supplementary
172, Dynamic Probabilistic Models for Latent Feature Propagation in Social Networks,
Creighton Heaukulani*, University of Cambridge; Ghahramani Zoubin, Cambridge University
abstract/pdf
828, Modeling Information Propagation with Survival Theory,
Manuel Gomez-Rodriguez*, Stanford University and MPI for Intelligent Systems; Jure Leskovec, Stanford; Bernhard Schölkopf, Max Planck Institute for Intelligent Systems
Spotlight Presentations:
1123, Learning Triggering Kernels for Multi-dimensional Hawkes Processes,
Ke Zhou*, Georgia Institute of Technology; Le Song, Georgia Tech; Hongyuan Zha, Computational Science and Engineering, Georgia Institute of Technology
369, Causal Estimation of Peer Influence Effects,
Edward Kao*, Harvard University; Panos Toulis, Harvard University; Edoardo Airoldi, Harvard; Donald Rubin, Harvard University
974, Modeling Temporal Evolution and Multiscale Structure in Networks,
Tue Herlau*, Technical University of Denmark; Morten Mørup, Technical University of Denmark; Mikkel Schmidt, Technical University of Denmark
544, Scalable Optimization of Neighbor Embedding for Visualization,
Zhirong Yang*, Aalto University; Jaakko Peltonen, Aalto University; Samuel Kaski, Aalto University
abstract/pdf/supplementary
Session III: 2:00 to 3:40
Monday, June 17, 2:00 to 3:40
Track A: Deep Learning 2
925, Learning the Structure of Sum-Product Networks,
Robert Gens*, University of Washington; Domingos Pedro, University of Washington
1129, Deep learning with COTS HPC systems,
Adam Coates*, Stanford; Brody Huval, Stanford University; Tao Wang, Stanford University; David Wu, Stanford University; Bryan Catanzaro, Stanford University; Ng Andrew, Stanford
93, Learning and Selecting Features Jointly with Point-wise Gated Boltzmann Machines,
Kihyuk Sohn*, University of Michigan; Guanyu Zhou; Chansoo Lee, University of Michigan; Honglak Lee, University of Michigan
abstract/pdf
1026, Regularization of Neural Networks using DropConnect,
Li Wan*, New York University; Matthew Zeiler, New York University; Sixin Zhang, New York University; Yann Le Cun, New York University; Rob Fergus, New York University
Spotlight Presentations:
502, Thurstonian Boltzmann Machines: Learning from Multiple Inequalities,
Truyen Tran*, Deakin University; Dinh Phung, Deakin University; Svetha Venkatesh, Deakin University
abstract/pdf/supplementary
279, Iterative Learning and Denoising in Convolutional Neural Associative Memories,
Amin Karbasi*, EPFL; Amir Hesam Salavati, EPFL; Amin Shokrollahi, EPFL
abstract/pdf/supplementary
457, No more pesky learning rates,
Tom Schaul*, NYU; Sixin Zhang, NYU; Yann LeCun, NYU
73, Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision Architectures,
James Bergstra*, Harvard University; Daniel Yamins; David Cox, Harvard University
abstract/pdf
Monday, June 17, 2:00 to 3:40
Track B: Compressed Sensing 2
680, Learning Heteroscedastic Models by Convex Programming under Group Sparsity,
Arnak Dalalyan*, ENSAE, CREST, LIGM; Mohamed Hebiri, Universit‚ Paris Est; Katia Meziani, Universit‚ Paris Dauphine; Joseph Salmon, Telecom ParisTech
58, Noisy Sparse Subspace Clustering,
Yu-Xiang Wang*, National University of Singapore; Huan Xu, National University of Singapore
abstract/pdf/supplementary
263, One-Bit Compressed Sensing: Provable Support and Vector Recovery,
Sivakant Gopi, IIT Bombay; Praneeth Netrapalli, University of Texas at Austin; Prateek Jain*, Microsoft Research; Aditya Nori, Microsoft Research India
403, Smooth Sparse Coding via Marginal Regression for Learning Sparse Representations,
Krishnakumar Balasubramanian*, Georgia Tech; Kai Yu, Baidu; Guy Lebanon, Georgia Tech
Spotlight Presentations:
599, Sparse projections onto the simplex,
Anastasios Kyrillidis*, EPFL; Stephen Becker, Paris 6 University; Volkan Cevher, EPFL; Christoph Koch, EPFL
abstract/pdf
1056, Intersecting singularities for multi-structured estimation,
Emile Richard*; Francis BACH; Jean-Philippe Vert, Ecole des Mines de Paris
29, Sparse Uncorrelated Linear Discriminant Analysis,
Xiaowei Zhang*, Department of Mathematics, National University of Singapore; Delin Chu, Department of Mathematics, National University of Singapore
abstract/pdf
350, Estimating Unknown Sparsity in Compressed Sensing,
Miles Lopes*, UC Berkeley, Dept. Statistics
Monday, June 17, 2:00 to 3:40
Track C: Reinforcement learning 2
955, Concurrent Reinforcement Learning from Customer Interaction Sequences,
David Silver*, UCL
100, Modelling Sparse Dynamical Systems with Compressed Predictive State Representations,
William Hamilton*, McGill University; Mahdi Milani Fard, McGill University; Joelle Pineau,
abstract/pdf
1199, Coco-Q: Learning in Stochastic Games with Side Payments,
Elizabeth Hilliard*, Brown University; Eric Sodomka, Brown University; Michael Littman, Brown; Amy Greenwald, Brown University
26, Guided Policy Search,
Sergey Levine*, Stanford University; Vladlen Koltun, Stanford University
1069, The Cross-Entropy Method Optimizes for Quantiles,
Sergiu Goschin*, Rutgers University; Ari Weinstein, Rutgers University; Michael Littman, Brown University
Monday, June 17, 2:00 to 3:40
Track D: Topic Modeling 1
617, A Practical Algorithm for Topic Modeling with Provable Guarantees,
Sanjeev Arora, Princeton; Rong Ge*, Princeton University; Yonatan Halpern, New York University; David Mimno, Princeton; Ankur Moitra; David Sontag, New York University; Yichen Wu, Princeton; Michael Zhu, Princeton University
abstract/pdf/supplementary
376, Online Latent Dirichlet Allocation with Infinite Vocabulary,
KE ZHAI*, University of Maryland; Jordan Boyd-Graber, University of Maryland
76, Gibbs Max-Margin Topic Models with Fast Sampling Algorithms,
Jun Zhu*, Tsinghua; Ning Chen, Tsinghua University; Hugh Perkins, Tsinghua University; Bo Zhang, Tsinghua University
abstract/pdf
Spotlight Presentations:
606, Modeling Musical Influence with Topic Models,
Uri Shalit*, Hebrew University of Jerusalem; Daphna Weinshall, Hebrew University of Jerusalem; Gal Chechik, Bar-Ilan University
abstract/pdf/supplementary
1184, Nested Chinese Restaurant Franchise Process: Applications to User Tracking and Document Modeling,
Amr Ahmed*; Liangjie Hong, Lehigh University; Alexander Smola, Google
61, Parallel Markov Chain Monte Carlo for Nonparametric Mixture Models,
Sinead Williamson*, Carnegie Mellon University; Avinava Dubey, Carnegie Mellon University; Eric Xing, Carnegie Mellon University
abstract/pdf/supplementary
354, MAD-Bayes: MAP-based Asymptotic Derivations from Bayes,
Tamara Broderick*, UC Berkeley; Brian Kulis, Ohio State; Michael Jordan, UC Berkeley
801, Topic Model Diagnostics: Assessing Domain Relevance via Topical Alignment,
Jason Chuang*, Stanford University; Sonal Gupta, Stanford University; Christopher Manning, Stanford University; Jeffrey Heer, Stanford University
Monday, June 17, 4:00 to 5:40
Track A: Deep Learning and Neuroscience
1051, On the importance of initialization and momentum in deep learning,
Ilya Sutskever*, University of Toronto; James Martens; George Dahl, University of Toronto; Geoffrey Hinton, University of Toronto
1055, Collaborative Filtering with Hybrid Restricted Boltzmann Machines,
Kostadin Georgiev; Preslav Nakov*, QCRI, Qatar Foundation
219, Parsing epileptic events using a Markov switching process model for correlated time series,
Drausin Wulsin*, University of Pennsylvania; Emily Fox, University of Washington; Brian Litt, University of Pennsylvania
abstract/pdf
611, Exploring the Mind: Integrating Questionnaires and fMRI,
Esther Salazar*, Duke University; Ryan Bogdan, Washington University; Adam Gorka, Duke University; Ahmad Hariri, Duke University; Lawrence Carin, Duke University
abstract/pdf
Spotlight Presentations:
552, Gated Autoencoders with Tied Input Weights,
Alain Droniou*, UPMC – ISIR; Olivier Sigaud, UPMC – ISIR
abstract/pdf
696, Simple Sparsification Improves Sparse Denoising Autoencoders in Denoising Highly Corrupted Images,
Kyunghyun Cho*, Aalto University
983, Natural Image Bases to Represent Neuroimaging Data,
Ashish Gupta*, University of Louisiana at LFT; Murat Ayhan, University of Louisiana at Lafayette; Anthony Maida, University of Louisiana at Lafayette
658, Direct Modeling of Complex Invariances for Visual Object Features,
Ka Yu Hui*, CUHK
abstract/pdf
Monday, June 17, 4:00 to 5:40
Track B: Compressed Sensing 3
693, Spectral Compressed Sensing via Structured Matrix Completion,
Yuxin Chen*, Stanford University; Yuejie Chi, Ohio State University
870, Sparse PCA through Low-rank Approximations,
Dimitris Papailiopoulos*, UT Austin; Alexandros Dimakis, UT Austin; Stavros Korokythakis, Stochastic Technologies
179, Efficient Sparse Group Feature Selection via Nonconvex Optimization,
Shuo Xiang*, Arizona State University; Xiaotong Shen, University of Minnesota; Jieping Ye, Arizona Sate University
abstract/pdf/supplementary
500, A General Iterative Shrinkage and Thresholding Algorithm for Non-convex Regularized Optimization Problems,
Pinghua Gong*, Tsinghua University; Changshui Zhang, Tsinghua University; Zhaosong Lu, Simon Fraser University; Jianhua Huang, ; Jieping Ye, Arizona Sate University
abstract/pdf
876, Robust Sparse Regression under Adversarial Corruption,
Yudong Chen*, University of Texas at Austin; Constantine Caramanis; Shie Mannor, Technion
Monday, June 17, 4:00 to 5:40
Track C: reinforcement learning and Time Series
840, ABC Reinforcement Learning,
Christos Dimitrakakis*, EPFL; Nikolaos Tziortziotis, University of Ioannina
393, Mean Reversion with a Variance Threshold,
Marco Cuturi*, Kyoto University; Alexandre d’Aspremont, CNRS / Ecole Polytechnique
1029, Gaussian Process Kernels for Pattern Discovery and Extrapolation,
Andrew Wilson*, University of Cambridge; Ryan Adams
Spotlight Presentations:
207, Average Reward Optimization Objective In Partially Observable Domains,
Yuri Grinberg*, McGill University; Doina Precup, McGill
abstract/pdf/supplementary
463, Planning by Prioritized Sweeping with Small Backups,
Harm van Seijen*, University of Alberta; Rich Sutton, University of Alberta
780, Dynamic Covariance Models for Multivariate Financial Time Series,
Yue Wu*, Cambridge University; Jose Miguel Hernandez-Lobato, Cambridge University; Ghahramani Zoubin, Cambridge University
300, Learning Sparse Penalties for Change-point Detection using Max Margin Interval Regression,
Toby Hocking*, INRIA; Guillem Rigaill; Jean-Philippe VERT; Francis BACH
670, Hierarchically-coupled hidden Markov models for learning kinetic rates from single-molecule data,
Jan-Willem Van de Meent*, Columbia University; Jonathan Bronson, Columbia University; Frank Wood, University of Oxford; Ruben Gonzalez, Jr., Columbia University; Chris Wiggins, Columbia University
abstract/pdf
529, Learning Connections in Financial Time Series,
Gartheeban Ganeshapillai*, MIT; John Guttag, MIT; Andrew Lo, MIT
abstract/pdf
1042, The Extended Parameter Filter,
Yusuf Bugra Erol*, UC Berkeley; Lei Li, UC Berkeley; Bharath Ramsundar, Stanford University; Russell Stuart, UC Berkeley
563, Transition Matrix Estimation in High Dimensional Time Series,
Fang Han*, Johns Hopkins University; Han Liu, Princeton University
abstract/pdf
Monday, June 17, 4:00 to 5:40
Track D: Topic Modeling 2
977, Dependent Normalized Random Measures,
Changyou Chen*, ANU & NICTA; Vinayak Rao; Yee Whye Teh; Wray Buntine, NICTA & ANU
1070, Topic Discovery through Data Dependent and Random Projections,
Weicong Ding*, Boston University; Mohammad Hossein Rohban, Boston University; Prakash Ishwar, Boston University; Venkatesh Saligrama
821, Factorial Multi-Task Learning : A Bayesian Nonparametric Approach,
Sunil Gupta*, Deakin University; Dinh Phung, Deakin University; Svetha Venkatesh, Deakin University
Spotlight Presentations:
1003, Scaling the Indian Buffet Process via Submodular Maximization,
Colorado Reed*, University of Cambridge; Ghahramani Zoubin, Cambridge University
506, A Variational Approximation for Topic Modeling of Hierarchical Corpora,
Do-kyum Kim*, University of California, San Diego; Geoffrey Voelker, University of California, San Diego; Lawrence Saul, University of California, San Diego
abstract/pdf/supplementary
1156, Manifold Perserving Hierarchical Topic Models for Quantization and Approximation,
Minje Kim*, University of Illinois; Paris Smaragdis, University of Illinois at Urbana-Champaign
607, Subtle Topic Models and Discovering Subtly Manifested Software Concerns Automatically ,
Mrinal Das*, Indian Institute of Science; Suparna Bhattacharya, IBM IRL; Chiranjib Bhattacharyya, Indian Institute of Science; Gopinath Kanchi, Indian Institute of Science
abstract/pdf/supplementary
852, Latent Dirichlet Allocation Topic Model with Soft Assignment of Descriptors to Words,
Daphna Weinshall*, Hebrew University; Gal Levi, Hebrew University; Dmitri Hanukaev, Hebrew University
692, Efficient Multi-label Classification with Many Labels,
Wei Bi*, Hong Kong University of Science and Technology; James Kwok
242, A Randomized Mirror Descent Algorithm for Large Scale Multiple Kernel Learning,
Arash Afkanpour*, University of Alberta; Andras Gyorgy, University of Alberta; Csaba Szepesvari, University of Alberta; Michael Bowling
abstract/pdf
112, MILEAGE: Multiple Instance LEArning with Global Embedding,
Dan Zhang*, Purdue University; Jingrui He, IBM; Luo Si, Purdue University; Richard Lawrence, IBM
Tuesday, June 18, 8:30 to 10:00
Keynote Speaker Santosh Vempala
Tuesday, June 18, 10:30 to 12:10
Track A: Feature Learning
508, Forecastable Component Analysis,
Georg Goerg*, Carnegie Mellon University
abstract/pdf/supplementary
107, Discriminatively Activated Sparselets,
Ross Girshick*, UC Berkeley; Hyun Oh Song, UC Berkeley; Trevor Darrell, UC Berkeley EECS and ICSI
abstract/pdf/supplementary
458, Multi-View Clustering and Feature Learning via Structured Sparsity,
Hua Wang*, Colorado School of Mines; Feiping Nie, University of Texas at Arlington; Heng Huang, University of Texas Arlington
126, Connecting the Dots with Landmarks: Discriminatively Learning Domain-Invariant Features for Unsupervised Domain Adaptation,
Boqing Gong, University of Southern California; Kristen Grauman; Fei Sha*, University of Southern California
abstract/pdf
Spotlight Presentations:
1202, On Nonlinear Generalization of Sparse Coding and Dictionary Learning,
Jeffrey Ho*, University of Florida; Yuchen Xie, Qualcomm; Baba Vemuri, University of Florida
891, Feature Multi-Selection among Subjective Features,
Sivan Sabato*, Microsoft; Adam Kalai, Microsoft Research
21, Sparsity-Based Generalization Bounds for Predictive Sparse Coding ,
Nishant Mehta*, Georgia Institute of Technolog; Alexander Gray, Georgia Institute of Technology
abstract/pdf/supplementary
788, A Unified Robust Regression Model for Lasso-like Algorithms,
Wenzhuo Yang*, National University of Singapore; Huan Xu, National University of Singapore
Tuesday, June 18, 10:30 to 12:10
Track B: Spectral Learning and Tensors
806, Spectral Learning of Hidden Markov Models from Dynamic and Static Data,
Tzu-Kuo Huang*, Carnegie Mellon University; Jeff Schneider
146, Learning Linear Bayesian Networks with Latent Variables,
Animashree Anandkumar, UCI; Daniel Hsu*, Microsoft Research; Adel Javanmard, Stanford University; Sham Kakade, Microsoft Research
abstract/pdf
1018, Spectral Experts for Estimating Mixtures of Linear Regressions,
Arun Tejasvi Chaganty*, Stanford University; Percy Liang, Stanford University
850, On learning parametric-output HMMs,
Aryeh Kontorovich*, Ben-Gurion University; Boaz Nadler, Weizmann Institute of Science; Roi Weiss, Ben-Gurion University
Spotlight Presentations:
283, Tensor Analyzers,
Yichuan Tang*, University of Toronto; Ruslan Salakhutdinov ; Geoffrey Hinton, University of Toronto
439, Unfolding Latent Tree Structures using 4th Order Tensors,
Mariya Ishteva*, Georgia Tech; Haesun Park, ; Le Song, Georgia Tech
448, Hierarchical Tensor Decomposition of Latent Tree Graphical Models,
Le Song*, Georgia Tech; Mariya Ishteva, Georgia Tech; Ankur Parikh, CMU; Eric Xing, CMU; Haesun Park
786, Infinite Positive Semidefinite Tensor Factorization with Application to Music Signal Analysis,
Kazuyoshi Yoshii*, AIST; Ryota Tomioka, University of Tokyo; Daichi Mochihashi, ISM; Masataka Goto, AIST
Tuesday, June 18, 10:30 to 12:10
Track C: Online Learning 1
805, Online Kernel Learning with a Near Optimal Sparsity Bound,
Lijun Zhang*, Michigan State University; Rong Jin, Michigan State University; Xiaofei He, Zhejiang University
710, On the Generalization Ability of Online Learning Algorithms for Pairwise Loss Functions,
Prateek Jain, Microsoft Research; Bharath Sriperumbudur, Gatsby Unit; Purushottam Kar*, IIT Kanpur; Harish Karnick, Indian Institute of Technology Kanpur
178, Thompson Sampling for Contextual Bandits with Linear Payoffs,
Shipra Agrawal*, Microsoft Research India; Navin Goyal, Microsoft Research India
1189, Online Learning under Delayed Feedback,
Pooria Joulani, University of Alberta; Andras Gyorgy*, University of Alberta; Csaba Szepesvari
1102, Almost Optimal Exploration in Multi-Armed Bandits,
Zohar Karnin, Yahoo!; Tomer Koren*, Technion; Oren Somekh, Yahoo! Labs
Tuesday, June 18, 10:30 to 12:10
Track D: General SVM and Decision Tree Methods
74, Multi-Class Classification with Maximum Margin Multiple Kernel,
Corinna Cortes, Google; Mehryar Mohri, NYU; Afshin Rostamizadeh*, Google Research
397, Top-down particle filtering for Bayesian decision trees,
Balaji Lakshminarayanan*, Gatsby Unit, UCL; Daniel Roy, ; Yee Whye Teh,
77, Cost-Sensitive Tree of Classifiers,
Zhixiang Xu*, Washington University; Matt Kusner, Washington University; Kilian Weinberger, Washington University, St. Louis; Minmin Chen, Washington University
abstract/pdf
Spotlight Presentations:
794, On the Statistical Consistency of Algorithms for Binary Classification under Class Imbalance,
Aditya Menon, UC San Diego; Harikrishna Narasimhan, Indian Institute of Science; Shivani Agarwal*, Indian Institute of Science; Sanjay Chawla, University of Sydney
790, Quickly Boosting Decision Trees — Pruning Underachieving Features Early,
Ron Appel*, Caltech; Thomas Fuchs, Caltech; Piotr Dollar, Microsoft; Pietro Perona
1185, Tree-Independent Dual-Tree Algorithms,
Ryan Curtin*, Georgia Institute of Technology; William March, Georgia Institute of Technology; Parikshit Ram, Georgia Institute of Technology; David Anderson, Georgia Institute of Technology; Alexander Gray, Georgia Institute of Technology; Charles Isbell,
767, Loss-Proportional Subsampling for Subsequent ERM,
Paul Mineiro*, Microsoft CISL; Nikos Karampatziakis, Microsoft
961, Saving Evaluation Time for the Decision Function in Boosting: Representation and Reordering Base Learner,
Peng Sun*, Tsinghua University; Jie Zhou, Tsignhua University
1157, Safe Screening of Non-Support Vectors in Pathwise SVM Computation,
Kohei Ogawa, Nagoya Institute of Technology; Yoshiki Suzuki, Nagoya Institute of Technology; Ichiro Takeuchi*, Nagoya Institute of technology
95, Convex formulations of radius-margin based Support Vector Machines,
Huyen Do*, University of Geneva; Alexandros Kalousis, University of Geneva
abstract/pdf
111, The Pairwise Piecewise-Linear Embedding for Efficient Non-Linear Classification,
Ofir Pele*, University of Pennsylvania ; Ben Taskar, University of Pennsylvania; Amir Globerson, The Hebrew University of Jerusalem; Michael Werman, The Hebrew University of Jerusalem
abstract, pdf
Tuesday, June 18, 2:00 to 3:40
Track A: Dimensionality Reduction
141,Principal Component Analysis on non-Gaussian Dependent Data,
Fang Han*, Johns Hopkins University; Han Liu, Princeton University
abstract/pdf
1103, Deep Canonical Correlation Analysis,
Galen Andrew*, University of Washington; Jeff Bilmes, University of Washington, Dept. of EE; Raman Arora, TTIC; Karen Livescu
654, Canonical Correlation Analysis based on Hilbert-Schmidt Independence Criterion and Centered Kernel Target Alignment,
Billy Chang*, Dalla Lana School of Public Health, University of Toronto; Uwe Kruger, Department of Mechanical and Industrial Engineering, Sultan Qaboos University; Rafal Kustra, Dalla Lana School of Public Health, University of Toronto; Junping Zhang, Fudan University
abstract/pdf/supplementary
408, Vanishing Component Analysis,
Roi Livni, HUJI; David Lehavi, Hp Research; Sagi Schein, Hp Research; Hila Nachliely, Hp Research; Shai Shalev-Shwartz, Hebrew University of Jerusalem; Amir Globerson*, Hebrew University
abstract/pdf
Spotlight Presentations:
1183, Fast algorithms for sparse principal component analysis based on Rayleigh quotient iteration,
Volodymyr Kuleshov*, Stanford University
215, Efficient Dimensionality Reduction for Canonical Correlation Analysis,
Haim Avron*, IBM TJ Watson Research Center; Christos Boutsidis ; Sivan Toledo ; Anastasios Zouzias, University of Toronto
abstract/pdf
205, Adaptive Sparsity in Gaussian Graphical Models ,
Eleanor Wong*, University of Utah; Suyash Awate, University of Utah; P. Thomas Fletcher, University of Utah
abstract/pdf
357, The Most Generative Maximum Margin Bayesian Networks,
Robert Peharz*, TU Graz; Sebastian Tschiatschek, TU Graz; Franz Pernkopf, TU Graz
Tuesday, June 18, 2:00 to 3:40
Track B: Statistical Methods
872, Computation-Risk Tradeoffs for Covariance-Thresholded Regression,
Dinah Shender*, University of Chicago; John Lafferty
769, Scalable Simple Random Sampling and Stratified Sampling,
Xiangrui Meng*, LinkedIn Corporation
1015, The lasso, persistence, and cross-validation
Darren Homrighausen*, Colorado State University; Daniel McDonald, Indiana University
889, Consistency versus Realizable H-Consistency for Multiclass Classification,
Phil Long*, NEC; Rocco Servedio, Columbia University
Spotlight Presentations:
738, Two-Sided Exponential Concentration Bounds for Bayes Error Rate and Shannon Entropy,
Jean Honorio*, CSAIL MIT; Jaakkola Tommi, MIT
1137, Scale Invariant Conditional Dependence Measures,
Sashank J Reddi*, Carnegie Mellon University; Barnabas Poczos,
865, Infinite Markov-Switching Maximum Entropy Discrimination Machines,
Sotirios Chatzis*, CUT
1020, Distribution to Distribution Regression,
Junier Oliva*, CMU; Barnabas Poczos; Jeff Schneider,
Tuesday, June 18, 2:00 to 3:40
Track C: Online Learning 2
367, Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning,
Odalric-Ambrym Maillard*, Montanuniversitaet Leoben; Phuong Nguyen, ANU College of Engineering and Computer Science; Ronald Ortner, Montanuniversitaet Leoben; Daniil Ryabko, INRIA Lille
abstract/pdf
89, Combinatorial Multi-Armed Bandit: General Framework, Results and Applications,
Wei Chen*, Microsoft Research Asia; Yajun Wang, Microsoft Research Asia; Yang Yuan, Cornell University
abstract/pdf/supplementary
387, Dynamical Models and tracking regret in online convex programming,
Eric Hall*, Duke University; Rebecca Willett, Duke University
833, Better Rates for Any Adversarial Deterministic MDPs,
Ofer Dekel, Microsoft; Elad Hazan*, Technion
Spotlight Presentations:
169, Multiple Identifications in Multi-Armed Bandits,
Sebastian Bubeck*, Princeton; Tengyao Wang; Nitin Viswanathan,
abstract/pdf
37, Gossip-based distributed stochastic bandit algorithms,
Balazs Szorenyi; Robert Busa-Fekete*, MTA-SZTE; Istvan Hegedus; Robert Ormandi; Mark Jelasity; Balazs Kegl, CNRS / University Paris-Sud
247, Dual Averaging and Proximal Gradient Descent for Online Alternating Direction Multiplier Method,
Taiji Suzuki*, University of Tokyo
abstract/pdf/supplementary
Tuesday, June 18, 2:00 to 3:40
Track D: * structured labeling
306, Learning from Human List Production,
Kwang-Sung Jun*, University of Wisconsin-Madiso; Jerry Zhu, University of Wisconsin.; Burr Settles, Carnegie Mellon University; Timothy Rogers, University of Wisconsin-Madison
346, A Structural SVM Based Approach for Optimizing Partial AUC,
Harikrishna Narasimhan*, Indian Institute of Science; Shivani Agarwal, Indian Institute of Science
abstract/pdf/supplementary
106, A Machine Learning Framework for Programming by Example,
Aditya Menon*, UC San Diego; Omer Tamuz; Sumit Gulwani, Microsoft Research; Butler Lampson, Microsoft Research; Adam Kalai, Microsoft Research
abstract/pdf
454, Convex Adversarial Collective Classification,
Mohamad Ali Torkamani*, University of Oregon; Daniel Lowd, University of Oregon
Spotlight Presentations:
954, Learning Convex QP Relaxations for Structured Prediction,
Jeremy Jancsary*, Microsoft Research Cambridge; Sebastian Nowozin, Microsoft Research Cambridge; Carsten Rother, Microsoft Research Cambridge
117, Fixed-Point Model For Structured Labeling,
Quannan Li; Jingdong Wang, Microsoft Research Asia; David Wipf; Zhuowen Tu*, Microsoft
abstract/pdf
310, A Generalized Kernel Approach to Structured Output Learning,
Hachem Kadri*, Aix-Marseille University/LIF; Mohammad Ghavamzadeh, INRIA Lille; Philippe Preux
abstract/pdf
1049, Optimizing the F-measure in Multi-label Classification: Plug-in Rule Approach versus Structured Loss Minimization,
Krzysztof Dembczynski*; Wojciech Kotlowski; Arkadiusz Jachnik, Poznan University of Technolog; Willem Waegeman, Ghent University; Eyke Huellermeier, Universitaet Marburg
Tuesday, June 18, 4:00 to 5:40
Track A: nearest neighbor and metric learning
746, Entropic Affinities: Properties and Efficient Numerical Computation,
Max Vladymyrov, UC Merced; Miguel Carreira-Perpinan*
86, Learning Hash Functions Using Column Generation,
Xi Li*, University of Adelaide; Guosheng Lin, University of Adelaide; Chunhua Shen; Anton van den Hengel; Anthony Dick, University of Adelaide
abstract/pdf
415, Robust Structural Metric Learning,
Daryl Lim*, UCSD; Gert Lanckriet, UCSD; Brian McFee, Columbia University
abstract/pdf
785, Revisiting the Nystrom method for improved large-scale machine learning,
Alex Gittens*, CalTech; Michael Mahoney, Stanford University
Spotlight Presentations:
743, That was fast! Speeding up NN search of high dimensional distributions.,
Emanuele Coviello*, UCSD; Adeel Mumtaz, City U Honk Kong; Antoni Chan, City University of Hong Kong; Gert Lanckriet, UCSD
339, Stochastic k-Neighborhood Selection for Supervised and Unsupervised Learning,
Daniel Tarlow*, University of Toronto; Kevin Swersky; Ilya Sutskever; Laurent Charlin, University of Toronto; Rich Zemel,
1126, Predictable Dual-View Hashing,
Mohammad Rastegari*, UMD; Jonghyun Choi, University of Maryland; Shobeir Fakhraei, University of Maryland; Daume Hal, University of Maryland; Larry Davis, University of Maryland
526, A unifying framework for vector-valued manifold regularization and multi-view learning,
Minh Ha Quang*, Istituto Italiano di Tecnologi; Loris Bazzani, Istituto Italiano di Tecnologia; Vittorio Murino, Istituto Italiano di Tecnologia
abstract/pdf/supplementary
Tuesday, June 18, 4:00 to 5:40
Track B: General Methods
183, Domain Adaptation for Sequence Labeling Tasks with a Probabilistic Language Adaptation Model,
Min Xiao, Temple University; Yuhong Guo*, Temple University
abstract/pdf
186, Maximum Variance Correction with Application to A* Search,
Wenlin Chen*, Washington University; Kilian Weinberger, Washington University St. Louis; Yixin Chen, Washington University
abstract/pdf
270, Learning with Marginalized Corrupted Features,
Laurens van der Maaten*, Delft University of Technology; Minmin Chen, Washington University; Stephen Tyree, Washington University in St. Louis; Kilian Weinberger, Washington University St. Louis
abstract/pdf
Spotlight Presentations:
285, Scaling Multidimensional Gaussian Processes using Projected Additive Approximations,
Elad Gilboa*, Washington University in St. Louis; Yunus Saatci; John Cunningham, Washington University at St. Louis
abstract/pdf/supplementary
1131, Nonparametric Mixture of Gaussian Processes with Constraints,
James Ross*, Northeastern University; Jennifer Dy, Northeastern University
967, Fast Dual Variational Inference for Non-Conjugate Latent Gaussian Models,
Mohammad Emtiyaz Khan*, Ecole Polytechnique Federale de Lausanne; Aleksandr Aravkin, University of British Columbia; Michael Friedlander, University of British Columbia, Vancouver; Matthias Seeger, EPFL
484, Gaussian Process Vine Copulas for Multivariate Dependence,
David Lopez-Paz*, Max Planck Institute for IS; Jose Miguel Hernandez-Lobato, Cambridge University; Ghahramani Zoubin, Cambridge University
abstract/pdf
1060, Structure Discovery in Nonparametric Regression through Compositional Kernel Search,
David Duvenaud, University of Cambridge; James Lloyd*, University of Cambridge; Roger Grosse, Massachusetts Institute of Technology; Joshua Tenenbaum, Massachusetts Institute of Technology; Ghahramani Zoubin, Cambridge University
594, Sequential Bayesian Search,
Zheng Wen*, Stanford University; Branislav Kveton, Technicolor Labs Palo Alto; Brian Eriksson, Technicolor Labs Palo Alto; Sandilya Bhamidipati, Technicolor Labs Palo Alto
abstract/pdf/pdf
923, Kernelized Bayesian Matrix Factorization,
Mehmet Gönen*, Aalto University; Suleiman Khan, Aalto University; Samuel Kaski, Aalto University
583, SADA: A General Framework to Support Robust Causation Discovery,
Ruichu Cai, GDUT; Zhenjie Zhang*, Advaned Digital Sciences Cente; Zhifeng Hao, South China University of Technology
abstract/pdf
Tuesday, June 18, 4:00 to 5:40
Track C: Transfer Learning
13, Domain Generalization via Invariant Feature Representation,
Krikamol Muandet*, MPI for Intelligent Systems; David Balduzzi, ETH Zurich; Bernhard Schoelkopf, MPI for Intelligent Systems
abstract/pdf/supplementary
868, A PAC-Bayesian Approach for Domain Adaptation with Specialization to Linear Classifiers,
Pascal Germain, Département d’informatique et de génie logiciel, Universit‚ Laval; Amaury Habrard, Laboratoire Hubert Curien, Universit‚ de Saint-Etienne; François Laviolette, Laval University; Emilie Morvant*, Aix-Marseille University, LIF-QARMA
657, Sparse coding for multitask and transfer learning,
Andreas Maurer; Massi Pontil; Bernardino Romera-Paredes*, University College London
abstract/pdf/supplementary
91, Bayesian Games for Adversarial Regression Problems,
Michael Groáhans*, Universitaet Potsdam; Christoph Sawade, Universitaet Potsdam; Michael Brückner, Universitaet Potsdam; Tobias Scheffer
Spotlight Presentations:
372, Joint Transfer and Batch-mode Active Learning,
Rita Chattopadhyay*, Arizona State University; Wei Fan, Huawei Noah’s Ark Lab; Ian Davidson, University of California, Davis; Sethuraman Panchanathan; Jieping Ye, Arizona Sate University
1187, Multilinear Multitask Learning,
Bernardino Romera-Paredes*, University College London; Hane Aung, University College London; Nadia Bianchi-Berthouze, University College London; Massimiliano Pontil, University College London
965, Stability and Hypothesis Transfer Learning,
Ilja Kuzborskij*, Idiap Research Institute; Francesco Orabona, TTI Chicago
695, Multi-Task Learning with Gaussian Matrix Generalized Inverse Gaussian Model,
Ming Yang*, Zhejiang University; Li Yingming, Zhejiang University; Zhang Zhongfei (Mark), Zhejiang University
Tuesday, June 18, 4:00 to 5:40
Track D: Statistical Learning and Inference
360, Convex Relaxations for Learning Bounded-Treewidth Decomposable Graphs,
Sesh Kumar K. S., INRIA; Francis Bach*, INRIA
abstract/pdf/supplementary
760, ˜SVM for Learning with Label Proportions,
Felix Yu*, Columbia University; Dong Liu, Columbia University; Sanjiv Kumar, Google Research; Jebara Tony, Columbia University; Shih-Fu Chang, Columbia University
1105, Consistency of Online Random Forests,
Misha Denil*, University of British Columbia; David Matheson, University of British Columbia; De Freitas Nando, University of British Columbia
Spotlight Presentations:
259, Inference algorithms for pattern-based CRFs on sequence data,
Rustem Takhanov*, IST Austria; Vladimir Kolmogorov, IST Austria
389, Relaxed expectation propagation based on l1-penalized KL minimization,
Yuan Qi*, Purdue University; Yandong Guo, Purdue University
324, A Fast and Exact Energy Minimization Algorithm for Cycle MRFs,
Huayan Wang*, Stanford University; Koller Daphne, Stanford University
571, Subproblem-Tree Calibration: A Unified Approach to Max-Product Message Passing,
Huayan Wang*, Stanford University; Koller Daphne, Stanford University
abstract/pdf/supplementary
993, Approximate Inference in Collective Graphical Models,
Daniel Sheldon*, University of Massachusetts Amherst; Tao Sun, University of Massachusetts Amherst; Akshat Kumar, IBM Research India; Tom Dietterich
628, An Adaptive Learning Rate for Stochastic Variational Inference,
Rajesh Ranganath*, Princeton University; Chong Wang; Blei David, Princeton; Eric Xing, CMU
abstract/pdf/supplementary
1101, The Bigraphical Lasso,
Alfredo Kalaitzis*, UCL; John Lafferty, University of Chicago; Neil Lawrence, University of Sheffield
1030, Anytime Representation Learning,
Zhixiang Xu*, Washington University; Matt Kusner, Washington University; Gao Huang, Tsinghua University; Kilian Weinberger, Washington University St. Louis
Wednesday, June 19, 8:30 to 10:00,
Keynote Speaker Vincent Vanhoucke
Wednesday, June 19, 10:30 to 12:10
Track A: Clustering
691, A Local Algorithm for Finding Well-Connected Clusters,
Silvio Lattanzi, Google Research; Vahab Mirrokni, Google Research; Zeyuan Allen Zhu*, MIT CSAIL
550, Monochromatic Bi-Clustering ,
Sharon Wulff*, ETH Zurich; Ruth Urner, University of Waterloo; Shai Ben-David, University of Waterloo
abstract/pdf/supplementary
424, Constrained fractional set programs and their application in local clustering and community detection,
Thomas B hler*, Saarland University; Shyam Sundar Rangapuram, Saarland University; Simon Setzer, Saarland University; Matthias Hein, Saarland University
987, Breaking the Small Cluster Barrier of Graph Clustering,
Nir Ailon*, Technion; Yudong Chen, University of Texas at Austin; Huan Xu, National University of Singapore
Spotlight Presentations:
555, Strict Monotonicity of Sum of Squares Error and Normalized Cut in the Lattice of Clusterings,
Nicola Rebagliati*, VTT – Finland
abstract/pdf
190, Clustering and Learning Behaviors using a Sparse Latent Space,
Lui Montesano*, University of Zaragoza; Manuel Lopes, INRIA; Javier Almingol, University of Zaragoza
545, Precision-recall space to correct external indices for biclustering,
Blaise Hanczar*, University Paris Descartes; Mohamed Nadif, University Paris Descartes
abstract/pdf
1171, Semi-supervised Clustering by Input Pattern Assisted Pairwise Similarity Matrix Completion,
Jinfeng Yi*, Michigan State University; Rong Jin, Michigan State University; Qi Qian, Michigan State University; Anil Jain, Michigan State University
Wednesday, June 19, 10:30 to 12:10
Track B: Optimization
48, Stochastic Gradient Descent for Non-smooth Optimization: Convergence Results and Optimal Averaging Schemes,
Ohad Shamir*, Microsoft Research; Tong Zhang
abstract/pdf
232, Optimal rates for stochastic convex optimization under Tsybakov noise condition,
Aaditya Ramdas*, CMU; Aarti Singh, CMU
abstract/pdf/supplementary
918, Fast Semidifferential-based Submodular Function Optimization,
Rishabh Iyer, University of Washington; Stefanie Jegelka*, University of California Berkeley; Jeff Bilmes, University of Washington, Dept. of EE
612, A proximal Newton framework for composite minimization: Graph learning without Cholesky decompositions and matrix inversions,
Quoc Tran Dinh*, LIONS, STL, IEL, EPFL; Anastasios Kyrillidis, EPFL; Volkan Cevher, EPFL
abstract/pdf/supplementary
Spotlight Presentations:
1008, Mini-Batch Primal and Dual Methods for SVMs,
Martin Takac*, University of Edinburgh; Avleen Bijral, TTI-C; Peter Richtarik, University of Edinburgh; Nati Srebro, TTI-Chicago
53, Stochastic Alternating Direction Method of Multipliers,
Hua Ouyang*, Georgia Tech; Niao He, Georgia Tech; Long Tran, Georgia Tech; Alexander Gray, Georgia Tech
abstract/pdf/supplementary
884, Optimization with First-Order Surrogate Functions,
Julien Mairal*, INRIA
41, Fast Probabilistic Optimization from Noisy Gradients,
Philipp Hennig*, Max Planck Society
abstract/pdf
Wednesday, June 19, 10:30 to 12:10
Track C: Invited Orals
394, Large-Scale Bandit Problems and KWIK Learning,
Jacob Abernethy, University of Pennsylvania; Kareem Amin*, University of Pennsylvania; Michael Kearns, University of Pennsylvania; Moez Draief, Imperial College
abstract/pdf/supplementary
Wednesday, June 19, 10:30 to 12:10
Track D: * Learning Theory
644, Margins, Shrinkage and Boosting,
Matus Telgarsky*, UCSD
abstract/pdf/supplementary
849, Sharp Generalization Error Bounds for Randomly-projected Classifiers,
Robert Durrant*, University of Birmingham; Ata Kaban, University of Birmingham
63, Risk Bounds and Learning Algorithms for the Regression Approach to Structured Output Prediction,
Sébastien Giguère, Laval University; Francois Laviolette, Laval University; Mario Marchand*, Laval University; Khadidja Sylla, Laval University
abstract/pdf/supplementary
898, Collective Stability and Structured Prediction: Generalization from One Example,
Ben London*, University of Maryland, College Park; Bert Huang, University of Maryland; Ben Taskar, University of Pennsylvania; Lise Getoor, University of Maryland
Spotlight Presentations:
54, Hierarchical Regularization Cascade for Joint Learning,
Alon Zweig*, Hebrew University; Daphna Weinshall, Hebrew University
443, Learning Fair Representations,
Rich Zemel*; Yu Wu, University of Toronto; Kevin Swersky; Toniann Pitassi; Cynthia Dwork,
173, Differentially Private Learning with Kernels,
Prateek Jain*, Microsoft Research; Abhradeep Thakurta, Pennsylvania State University
461, Rounding Methods for Discrete Linear Classification,
Yann Chevaleyre*, Lipn; Frederick Koriche, Lirmm; Jean-Daniel Zucker, IRD
abstract/pdf/supplementary
Wednesday, June 19, 2:00 to 3:40
Track A: Dimensionality Reduction and Semi-Supervised Learning
27, Squared-loss Mutual Information Regularization,
Gang Niu*, Tokyo Institute of Technology; Wittawat Jitkrittum; Bo Dai, ; Hirotaka Hachiya; Masashi Sugiyama
509, Ellipsoidal Multiple Instance Learning,
Gabriel Krummenacher*, ETH Zurich; Cheng Soon Ong, NICTA Melbourne; Joachim Buhmann, ETH Zurich
abstract/pdf/supplementary
933, Infinitesimal Annealing for Training Semi-Supervised Support Vector Machine,
Kohei Ogawa, Nagoya Institute of Technology; Motoki Imamura, Nagoya Institute of Technology; Ichiro Takeuchi*, Nagoya Institute of technology; Masashi Sugiyama
1108, Sparse Gaussian Conditional Random Fields: Algorithms, and Application to Energy Forecasting,
Matt Wytock, CMU; Zico Kolter*, CMU
1198, Adaptive Hamiltonian and Riemann Manifold Monte Carlo,
Ziyu Wang*, University of British Columbia; Shakir Mohamed; De Freitas Nando, University of British Columbia
Wednesday, June 19, 2:00 to 3:40
Track B: Optimization and Integration
487, Stochastic Simultaneous Optimistic Optimization,
Michal Valko*, INRIA; Alexandra Carpentier, University of Cambridge; Remi Munos, INRIA Lille
abstract/pdf
36, Block-Coordinate Frank-Wolfe Optimization for Structural SVMs,
Simon Lacoste-Julien*, INRIA / ENS; Martin Jaggi, Ecole Polytechnique, CNRS; Mark Schmidt, INRIA; Patrick Pletscher, ETH
abstract/pdf
656, Taming the Curse of Dimensionality: Discrete Integration by Hashing and Optimization,
Stefano Ermon*, Cornell University; Carla Gomes, Cornell University; Ashish Sabharwal, IBM Watson Research Center; Bart Selman, Cornell University
abstract/pdf/supplementary
Spotlight Presentations:
1116, Expensive Function Optimization with Stochastic Binary Outcomes,
Matthew Tesch*, Carnegie Mellon University; Jeff Schneider, Carnegie Mellon University; Howie Choset, Carnegie Mellon University
1047, O(logT) Projections for Stochastic Optimization of Smooth and Strongly Convex Functions,
Lijun Zhang*, Michigan State University; Tianbao Yang, GE Global Research; Rong Jin, Michigan State University; Xiaofei He, Zhejiang University
275, Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization,
Martin Jaggi*, Ecole Polytechnique, CNRS
abstract/pdf/supplementary
1036, Algorithms for Direct 0–1 Loss Optimization in Binary Classification,
Tan Nguyen, Australian National University; Scott Sanner*
488, Toward Optimal Stratification for Stratified Monte-Carlo Integration,
Alexandra Carpentier*, University of Cambridge; Remi Munos, INRIA Lille
abstract/pdf
Wednesday, June 19, 2:00 to 3:40
Track C: Vision
10, An Optimal Policy for Target Localization with Application to Electron Microscopy,
Raphael Sznitman*, EPFL; Aurelien Lucchi, EPFL; Peter Frazier, Cornell University; Bruno Jedynak, Johns Hopkins University; Pascal Fua, EPFL
abstract/pdf
1115, Fast Image Tagging,
Minmin Chen*, Washington University; Alice Zheng, Microsoft Research; Kilian Weinberger, Washington University St. Louis
348, An Efficient Posterior Regularized Latent Variable Model for Interactive Sound Source Separation,
Nicholas Bryan*, Stanford University; Gautham Mysore, Advanced Technology Labs, Adobe Systems Inc.
Spotlight Presentations:
904, Max-Margin Multiple-Instance Dictionary Learning,
Xinggang Wang; Zhuowen Tu*, Microsoft
761, Parameter Learning and Convergent Inference for Dense Random Fields,
Philipp Kraehenbuehl*, Stanford University; Vladlen Koltun, Stanford University
418, Can We Recognize Tiger by Bus Images? _ Robust and Discriminative Self-Taught Image Categorization,
Hua Wang*, Colorado School of Mines; Feiping Nie, University of Texas at Arlington; Heng Huang, University of Texas Arlington
886, Learning Spatio-Temporal Structure from RGB-D Videos for Human Activity Detection and Forecasting,
Hema Koppula*, Cornell University; Ashutosh Saxena, Cornell University
15, A Spectral Learning Approach to Range-Only SLAM,
Byron Boots*, CMU; Geoff Gordon, CMU
abstract/pdf/supplementary
726, Non-Linear Stationary Subspace Analysis with Application to Video Classification,
Mahsa Baktashmotlagh*, University of Queensland; Mehrtash Harandi, NICTA; Abbas Bigdeli, UQ; Brian Lovell, UQ; Mathieu Salzmann
776, On Compact Codes for Spatially Pooled Features,
Yangqing Jia*, UC Berkeley; Oriol Vinyals, UC Berkeley; Trevor Darrell, UC Berkeley EECS and ICSI
812, Analogy-preserving Semantic Embedding for Visual Object Categorization,
Sung Ju Hwang*, University of Texas, Austin; Kristen Grauman; Fei Sha, University of Southern California
Wednesday, June 19, 2:00 to 3:40
Track D: Learning Theory II
1043, Exploiting Ontology Structures and Unlabeled Data for Learning,
Nina Balcan, Georgia Tech; Avrim Blum*, Carnegie Mellon University; Yishay Mansour, Hebrew University
952, One-Pass AUC Optimization,
Wei Gao*, Nanjing University; Rong Jin, Michigan State University; Shenghuo Zhu; Zhi-Hua Zhou, Nanjing University
16, Near-Optimal Bounds for Cross-Validation via Loss Stability,
Ravi Kumar*, Google; Daniel Lokshtanov; Sergei Vassilvitskii; Andrea Vattani,
abstract/pdf
820, Algebraic classifiers: a generic approach to fast cross-validation,parallel training,
Michael Izbicki*, UC Riverside
Spotlight Presentations:
1041, Top-k Selection based on Adaptive Sampling of Noisy Preferences,
Robert Busa-Fekete*, MTA-SZTE; Balazs Szorenyi; Weiwei Cheng, University of Marburg; Paul Weng; Eyke Huellermeier, Universitaet Marburg
319, Enhanced statistical rankings via targeted data collection,
Braxton Osting*, UCLA; Christoph Brune, UCLA; Stanley Osher, UCLA
abstract/pdf
138, Efficient Ranking from Pairwise Comparisons,
Fabian Wauthier*, UC Berkeley; Nebojsa Jojic, Microsoft; Michael Jordan, UC Berkeley
903, Stable Coactive Learning via Perturbation,
Karthik Raman*, Cornell University; Thorsten Joachims, Cornell; Pannaga Shivaswamy, AT&T; Tobias Schnabel, University of Stuttgart
Wednesday, June 19, 4:00 to 5:40
Track A: Matrix Factorization
135, Fast Conical Hull Algorithms for Near-separable Non-negative Matrix Factorization,
Abhishek Kumar*, University of Maryland, CP; Vikas Sindhwani, IBM Research; Prabhanjan Kambadur, IBM Research
abstract/pdf
278, General Functional Matrix Factorization Using Gradient Boosting,
Tianqi Chen*, Shanghai Jiao Tong University; Hang Li, Huawei Noah’s Ark Lab, Hong Kong; Qiang Yang, Hong Kong University of Science and Technology; Yong Yu, Shanghai Jiao Tong University
abstract/pdf
981, Fast Max-Margin Matrix Factorization with Data Augmentation,
Minjie Xu*, Tsinghua University; Jun Zhu, Tsinghua; Bo Zhang, Tsinghua University
513, Local Low-Rank Matrix Approximation,
Joonseok Lee*, Georgia Tech; Seungyeon Kim, Georgia Institute of Technology; Guy Lebanon, Georgia Tech; Yoram Singer, Google
abstract/pdf
Spotlight Presentations:
1174, Learning the beta-Divergence in Tweedie Compound Poisson Matrix Factorization Models,
Umut Simsekli*, Bogazici University; Yusuf Kenan Yilmaz, Bogazici University; Ali Taylan Cemgil, Bogazici University
343, ELLA: An Efficient Lifelong Learning Algorithm,
Paul Ruvolo*, Bryn Mawr College; Eric Eaton, Bryn Mawr College
abstract/pdf/supplementary
772, Riemannian Similarity Learning,
Li Cheng*, A*STAR
1120, Multiple-Source Cross Validation,
Krzysztof Geras*, University of Edinburgh; Charles Sutton, University of Edinburgh
Wednesday, June 19, 4:00 to 5:40
Track B: Kernel Methods
751, Local Deep Kernel Learning for Efficient Non-linear SVM Prediction,
Cijo Jose, Indian Institute of Technology – Delhi Microsoft; Prasoon Goyal, Indian Institute of Technology – Delhi; Parv Aggrwal, Indian Institute of Technology; Manik Varma*, Microsoft Research India
361, Fastfood – Computing Hilbert Space Expansions in loglinear time,
Quoc Le, Google; Tamas Sarlos, Google; Alexander Smola*, Google
1063, Smooth Operators and an RKHS Integration Approach,
Steffen Grunewalder*; Gretton Arthur, University College London; John Shawe-Taylor, University College London
895, Domain Adaptation under Target and Conditional Shift,
Kun Zhang*, Max Planck Institute for Intelligent Systems; Bernhard Schoelkopf, Max Planck Institute for Intelligent Systems; Krikamol Muandet, Max Planck Institute for Intelligent Systems; Zhikun Wang, Max Planck Institute for Intelligent Systems
Spotlight Presentations:
171, Learning Optimally Sparse Support Vector Machines,
Andrew Cotter*, TTI-C; Shai Shalev-Shwartz, Hebrew University of Jerusalem; Nati Srebro, TTI-Chicago
abstract/pdf/supplementary
262, A New Frontier of Kernel Design for Structured Data,
Kilho Shin*, University of Hyogo
abstract/pdf
384 ,Characterizing the Representer Theorem,
Yaoliang Yu*, University of Alberta; Hao Cheng, University of Alberta; Dale Schuurmans, University of Alberta; Csaba Szepesvari
abstract/pdf
683, Covariate Shift in Hilber Space: A Solution Via Sorrogate Kernels,
Kai Zhang*, Siemens Corporate Research; Vincent Zheng, Advanced Digital Science Center; QIaojun Wang, ; James Kwok; Qiang Yang, Hong Kong University of Science and Technology
Wednesday, June 19, 4:00 to 5:40
Track C: Crowd Sourcing and Large Scale Learning
96, Optimistic Knowledge Gradient Policy for Optimal Budget Allocation in Crowdsourcing,
Xi Chen*, Carnegie Mellon University; Qihang Lin, Carnegie Mellon University; Dengyong Zhou, Microsoft
926, Quantile Regression for Large-scale Applications,
Michael Mahoney*, Stanford University; Jiyan Yang, Stanford University; Xiangrui Meng, LinkedIn Corporation
621, Distributed training of Large-scale Logistic models,
Siddharth Gopal*, CMU; Yiming Yang
abstract/pdf
570, Label Partitioning For Sublinear Ranking,
Jason Weston*, Google Research; Ameesh Makadia, Google; Hector Yee, Google
abstract/pdf
Spotlight Presentations:
213, Human Boosting,
Harsh Pareek*, University of Texas Austin; Pradeep Ravikumar, University of Texas, Austin
abstract/pdf/supplementary
655, Large-Scale Learning with Less RAM via Randomization,
Daniel Golovin, Google, Inc.; D. Sculley*; Brendan McMahan, Google, Inc.; Michael Young, Google, Inc.
abstract/pdf
930, Robust Regression on MapReduce,
Michael Mahoney*, Stanford University; Xiangrui Meng, LinkedIn Corporation
366, Adaptive Task Assignment for Crowdsourced Classification,
Chien-Ju Ho*, UCLA; Shahin Jabbari, UCLA; Jennifer Wortman Vaughan, UCLA and Microsoft Research
abstract/pdf
Wednesday, June 19, 4:00 to 5:40
Track D: Learning Theory 3
675, Activized Learning with Uniform Classification Noise,
Liu Yang*, Carnegie Mellon University; Steve Hanneke, Carnegie Mellon University
abstract/pdf
316, Efficient Active Learning of Halfspaces: an Aggressive Approach,
Alon Gonen*, The Hebrew University; Sivan Sabato, Microsoft; Shai Shalev-Shwartz, Hebrew University of Jerusalem
abstract/pdf
1091, Selective sampling algorithms for cost-sensitive multiclass prediction,
Alekh Agarwal*, Berkeley
521, Generic Exploration and K-armed Voting Bandits,
Tanguy Urvoy*, Orange-labs; Fabrice Clerot, Orange-labs; Raphael Feraud, Orange-labs; Sami Naamane, Orange-labs
abstract/pdf/supplementary
Spotlight Presentations:
433, Efficient Semi-supervised and Active Learning of Disjunctions,
Nina Balcan, Georgia Institute of Technology; Christopher Berlind*, Georgia Institute of Technology; Steven Ehrlich, Georgia Institute of Technology; Yingyu Liang, Georgia Institute of Technology
abstract/pdf/supplementary
1158, Cost-sensitive Multiclass Classification Risk Bounds,
Bernardo Pires*; Csaba Szepesvari; Mohammad Ghavamzadeh, INRIA Lille
308, Active Learning for Multi-Objective Optimization,
Marcela Zuluaga*, ETH Zurich; Guillaume Sergent, ENS Lyon; Andreas Krause, ETH Zurich; Markus Pueschel, ETH Zurich
abstract/pdf/supplementary
90, Near-optimal Batch Mode Active Learning and Adaptive Submodular Optimization,
Yuxin Chen*, ETH Zurich; Andreas Krause, ETH Zurich
abstract/pdf/supplementary
Thursday & Friday, June 20 & 21, 8:30 – 5:30
Workshop Schedule
| 8:30 | Session 1 |
| 10:00 | Coffee |
| 10:30 | Session 2 |
| 12:00 | Lunch |
| 2:00 | Session 3 |
| 3:30 | Coffee |
| 4:00 | Session 4 |
| 5:30 | End |