Schedule
Pdf version with practical information
Conference venue: University of Helsinki, Main building, Fabianinkatu 33
Saturday July 5, 2008 | |||
| Breakfast in hotel | |||
| 8:00 am - | Registration (1st [ground] floor) | ||
| 9:00 am - 11:30 am | Tutorials T1, T2 and T3 | ||
| T1 Painless embeddings of distributions: the function space view. Alex Smola, Arthur Gretton and Kenji Fukumizu (S13, 3rd floor) [course page] | |||
| T2 Stochastic optimal control theory. Bert Kappen, Marc Toussaint (S5, 3rd floor) [course page] | |||
| T3 Dimensionality Reduction the Probabilistic Way. Neil Lawrence (S1, 2nd floor) [course page] | |||
| 11:30 am - 1:00 pm | Lunch (on your own) | ||
| 1:00 pm - 3:30 pm | Tutorials T4, T5 and T6 | ||
| T4 Graphical models and variational methods: Message-passing and relaxations. Martin Wainwright (S1, 2nd floor) [course page] | |||
| T5 Playing Machines: Machine Learning Applications in Computer Games. Ralf Herbrich, Thore Graepel (S5, 3rd floor) [course page] | |||
| T6 Beyond Convexity: Submodularity in Machine Learning. Andreas Krause, Carlos Guestrin (S13, 3rd floor) [course page] | |||
| 3:30 pm - 4:00 pm | Coffee Break (2nd, 3rd and 4th floors) | ||
| 4:00 pm - 6:30 pm | Tutorials T7, T8 and T9 | ||
| T7 Tutorial on Theory and Applications of Online Learning. Shai Shalev-Shwartz, Yoram Singer (S1, 2nd floor) [course page] | |||
| T8 Visual Object Recognition and Retrieval. Rob Fergus (S13, 3rd floor) [course page] | |||
| T9 Sparse Linear Models: Bayesian Inference and Experimental Design. Matthias Seeger (SH, 4th floor) [course page] | |||
Sunday July 6, 2008 | |||
| Breakfast in hotel | |||
| 8:00 am - | Registration (1st [ground] floor) | ||
| 8:30 am - 8:45 am | Opening (S1, 2nd floor) | ||
| 8:45 am - 9:45 am | Invited Talk: John Winn, Microsoft Research Cambridge: Probabilistic models for understanding images (S1, 2nd floor) | ||
| 9:45 am - 10:15 am | Coffee Break (2nd, 3rd and 4th floors) | ||
| 10:15 am - 11:55 am | 5 parallell sessions | ||
| Kernels (Sun 10:15 am, S1, 2nd floor) Session chair: Chris Williams | |||
| 10:15 am - 10:40 am | Paper #377: Tailoring Density Estimation via Reproducing Kernel Moment Matching. Le Song, Xinhua Zhang, Alex Smola, Arthur Gretton, and Bernhard Schoelkopf. [Abstract] [Full paper] [Discussion] | ||
| 10:40 am - 11:05 am | Paper #277: Nonextensive Entropic Kernels. Andre F. T. Martins, Mario A. T. Figueiredo, Pedro M. Q. Aguiar, Noah A. Smith, and Eric P. Xing. [Abstract] [Full paper] [Discussion] | ||
| 11:05 am - 11:30 am | Paper #216: Nu-Support Vector Machine as Conditional Value-at-Risk Minimization. Akiko Takeda and Masashi Sugiyama. [Abstract] [Full paper] [Discussion] | ||
| 11:30 am - 11:55 am | Paper #643: A Generalization of Haussler's Convolution Kernel - Mapping Kernel. Kilho Shin and Tetsuji Kuboyama. [Abstract] [Full paper] [Discussion] | ||
| Clustering (Sun 10:15 am, S5, 3rd floor) Session chair: Michèle Sebag | |||
| 10:15 am - 10:40 am | Paper #628: A Rate-Distortion One-Class Model and its Applications to Clustering. Koby Crammer, Partha Pratim Talukdar, and Fernando Pereira. [Abstract] [Full paper] [Discussion] | ||
| 10:40 am - 11:05 am | Paper #196: Estimating Local Optimums in EM Algorithm over Gaussian Mixture Model. Zhenjie Zhang, Bing Tian Dai, and Anthony K.H. Tung. [Abstract] [Full paper] [Discussion] | ||
| 11:05 am - 11:30 am | Paper #236: A Decoupled Approach to Exemplar-based Unsupervised Learning. Sebastian Nowozin and Gökhan Bakir. [Abstract] [Full paper] [Discussion] | ||
| 11:30 am - 11:55 am | Paper #168: Efficient MultiClass Maximum Margin Clustering. Bin Zhao, Fei Wang, and Changshui Zhang. [Abstract] [Full paper] [Discussion] | ||
| Hidden Markov Models (Sun 10:15 am, S12, 3rd floor) Session chair: Michael Collins | |||
| 10:15 am - 10:40 am | Paper #182: Inverting the Viterbi Algorithm: an Abstract Framework for Structure Design. Michael Schnall-Levin, Leonid Chindelevitch, and Bonnie Berger. [Abstract] [Full paper] [Discussion] | ||
| 10:40 am - 11:05 am | Paper #305: An HDP-HMM for Systems with State Persistence. Emily Fox, Erik Sudderth, Michael Jordan, and Alan Willsky. [Abstract] [Full paper] [Discussion] | ||
| 11:05 am - 11:30 am | Paper #413: Modeling Interleaved Hidden Processes. Niels Landwehr. [Abstract] [Full paper] [Discussion] | ||
| 11:30 am - 11:55 am | Paper #679: Beam Sampling for the Infinite Hidden Markov Model. Jurgen Van Gael, Yunus Saatci, Yee Whye Teh, and Zoubin Ghahramani. [Abstract] [Full paper] [Discussion] | ||
| Reinforcement Learning 1 - Domain Representation (Sun 10:15 am, S13, 3rd floor) Session chair: Richard Sutton | |||
| 10:15 am - 10:40 am | Paper #571: An Object-Oriented Representation for Efficient Reinforcement Learning. Carlos Diuk, Andre Cohen, and Michael Littman. [Abstract] [Full paper] [Discussion] | ||
| 10:40 am - 11:05 am | Paper #544: Hierarchical Model-Based Reinforcement Learning: R-max + MAXQ. Nicholas Jong and Peter Stone. [Abstract] [Full paper] [Discussion] | ||
| 11:05 am - 11:30 am | Paper #682: On the Hardness of Finding Symmetries in Markov Decision Processes. Shravan Narayanamurthy and Balaraman Ravindran. [Abstract] [Full paper] [Discussion] | ||
| 11:30 am - 11:55 am | Paper #580: Reinforcement Learning in the Presence of Rare Events. Jordan Frank, Shie Mannor, and Doina Precup. [Abstract] [Full paper] [Discussion] | ||
| Graphs (Sun 10:15 am, SH, 4th floor) Session chair: Eric Xing | |||
| 10:15 am - 10:40 am | Paper #379: Graph Kernels Between Point Clouds. Francis Bach. [Abstract] [Full paper] [Discussion] | ||
| 10:40 am - 11:05 am | Paper #681: Message-passing for Graph-structured Linear Programs: Proximal Projections, Convergence and Rounding Schemes. Pradeep Ravikumar, Alekh Agarwal, and Martin J. Wainwright. [Abstract] [Full paper] [Discussion] | ||
| 11:05 am - 11:30 am | Paper #565: Fast Incremental Proximity Search in Large Graphs. Purnamrita Sarkar, Andrew Moore, and Amit Prakash. [Abstract] [Full paper] [Discussion] | ||
| 11:30 am - 11:55 am | Paper #396: The Skew Spectrum of Graphs. Risi Kondor and Karsten Borgwardt. [Abstract] [Full paper] [Discussion] | ||
| 12:00 pm - 1:30 pm | Lunch (on your own) | ||
| 1:30 pm - 3:10 pm | 5 parallell sessions | ||
| Active Learning and Experimental Design (Sun 1:30 pm, S1, 2nd floor) Session chair: Sunita Sarawagi | |||
| 1:30 pm - 1:55 pm | Paper #324: Hierarchical sampling for active learning. Sanjoy Dasgupta and Daniel Hsu. [Abstract] [Full paper] [Discussion] | ||
| 1:55 pm - 2:20 pm | Paper #437: Active Kernel Learning. Steven C.H. Hoi and Rong Jin. [Abstract] [Full paper] [Discussion] | ||
| 2:20 pm - 2:45 pm | Paper #687: Actively Learning Level-Sets of Composite Functions. Brent Bryan and Jeff Schneider. [Abstract] [Full paper] [Discussion] | ||
| 2:45 pm - 3:10 pm | Paper #272: Learning from Incomplete Data with Infinite Imputations. Uwe Dick, Peter Haider, and Tobias Scheffer. [Abstract] [Full paper] [Discussion] | ||
| Distance Learning and Efficient Use (Sun 1:30 pm, S5, 3rd floor) Session chair: Lawrence Saul | |||
| 1:30 pm - 1:55 pm | Paper #215: Fast Solvers and Efficient Implementations for Distance Metric Learning. Kilian Weinberger and Lawrence Saul. [Abstract] [Full paper] [Discussion] | ||
| 1:55 pm - 2:20 pm | Paper #178: Nearest Hyperdisk Methods for High-Dimensional Classification. Hakan Cevikalp, Bill Triggs, and Robi Polikar. [Abstract] [Full paper] [Discussion] | ||
| 2:20 pm - 2:45 pm | Paper #400: Fast Nearest Neighbor Retrieval for Bregman Divergences. Lawrence Cayton. [Abstract] [Full paper] [Discussion] | ||
| 2:45 pm - 3:10 pm | Paper #340: Deep Learning via Semi-Supervised Embedding. Jason Weston, Frederic Ratle, and Ronan Collobert. [Abstract] [Full paper] [Discussion] | ||
| Optimization (Sun 1:30 pm, S12, 3rd floor) Session chair: Carlos Guestrin | |||
| 1:30 pm - 1:55 pm | Paper #327: Efficiently Solving Convex Relaxations for MAP Estimation. Pawan Kumar Mudigonda and Philip Torr. [Abstract] [Full paper] [Discussion] | ||
| 1:55 pm - 2:20 pm | Paper #461: A Quasi-Newton Approach to Nonsmooth Convex Optimization. Jin Yu, S.V.N. Vishwanathan, Simon Guenter, and Nicol Schraudolph. [Abstract] [Full paper] [Discussion] | ||
| 2:20 pm - 2:45 pm | Paper #497: Stopping Conditions for Exact Computation of Leave-One-Out Error in Support Vector Machines. Vojtech Franc, Pavel Laskov, and Klaus-R. Mueller. [Abstract] [Full paper] [Discussion] | ||
| 2:45 pm - 3:10 pm | Paper #260: On Partial Optimality in Multi-label MRFs. Pushmeet Kohli, Alexander Shekhovtsov, Carsten Rother, Vladimir Kolmogorov, and Philip Torr. [Abstract] [Full paper] [Discussion] | ||
| Reinforcement Learning 2 - Value Representation and Online Learning (Sun 1:30 pm, S13, 3rd floor) Session chair: Satinder Baveja | |||
| 1:30 pm - 1:55 pm | Paper #341: Online Kernel Selection for Bayesian Reinforcement Learning. Joseph Reisinger, Peter Stone, and Risto Miikkulainen. [Abstract] [Full paper] [Discussion] | ||
| 1:55 pm - 2:20 pm | Paper #125: A Worst-Case Comparison Between Temporal Difference and Residual Gradient with Linear Function Approximation. Lihong Li. [Abstract] [Full paper] [Discussion] | ||
| 2:20 pm - 2:45 pm | Paper #317: On-line Discovery of Temporal-Difference Networks. Takaki Makino and Toshihisa Takagi. [Abstract] [Full paper] [Discussion] | ||
| 2:45 pm - 3:10 pm | Paper #242: Prediction with Expert Advice for the Brier Game. Vladimir Vovk and Fedor Zhdanov. [Abstract] [Full paper] [Discussion] | ||
| Mixture Models, Dirichlet Processes (Sun 1:30 pm, SH, 4th floor) Session chair: Yee Whye Teh | |||
| 1:30 pm - 1:55 pm | Paper #460: Statistical Models for Partial Membership. Katherine Heller, Sinead Williamson, and Zoubin Ghahramani. [Abstract] [Full paper] [Discussion] | ||
| 1:55 pm - 2:20 pm | Paper #538: The Dynamic Hierarchical Dirichlet Process. Lu Ren, David B. Dunson, and Lawrence Carin. [Abstract] [Full paper] [Discussion] | ||
| 2:20 pm - 2:45 pm | Paper #554: Hierarchical Kernel Stick-Breaking Process for Multi-Task Image Analysis. Qi An, Chunping Wang, Ivo Shterev, Eric Wang, Lawrence Carin, and David B. Dunson. [Abstract] [Full paper] [Discussion] | ||
| 2:45 pm - 3:10 pm | Paper #502: Data Spectroscopy: Learning Mixture Models using Eigenspaces of Convolution Operators. Tao Shi, Mikhail Belkin, and Bin Yu. [Abstract] [Full paper] [Discussion] | ||
| 3:10 pm - 3:40 pm | Coffee Break (2nd, 3rd and 4th floors) | ||
| Award Paper Joint Session (Sun 3:40 pm, S1, 2nd floor) Session chair: Carlos Guestrin | |||
| 3:40 pm - 4:05 pm | Combining labeled and unlabeled data with co-training. Avrim Blum, Tom Mitchell (COLT-1998) [Full paper] | ||
| 4:05 pm - 4:30 pm | Paper #588: An Asymptotic Analysis of Generative, Discriminative, and Pseudolikelihood Estimators. Percy Liang and Michael Jordan. [Abstract] [Full paper] [Discussion] | ||
| 4:30 pm - 4:55 pm | Paper #627: Knows What It Knows: A Framework For Self-Aware Learning. Lihong Li, Michael Littman, and Thomas Walsh. [Abstract] [Full paper] [Discussion] | ||
| 4:55 pm - 5:20 pm | Paper #266: SVM Optimization: Inverse Dependence on Training Set Size. Shai Shalev-Shwartz and Nathan Srebro. [Abstract] [Full paper] [Discussion] | ||
| 5:20 pm - 5:45 pm | Paper #452: Learning for Control from Multiple Demonstrations. Adam Coates, Pieter Abbeel, and Andrew Ng. [Abstract] [Full paper] [Discussion] | ||
| 6:00 pm - 8:30 pm | Poster Session I (2nd & 3rd floors, with snacks): Posters from sessions Kernels (Sun 10:15 am) upto and including Sequence Data (Mon 1:30 pm) | ||
Monday July 7, 2008 | |||
| Breakfast in hotel | |||
| 8:00 am - | Registration (1st [ground] floor) | ||
| 8:30 am - 9:30 am | Invited Talk: Luc De Raedt, Katholieke Universiteit Leuven: Logical and Relational Learning Revisited (S1, 2nd floor) | ||
| 9:30 am - 10:00 am | Coffee Break (2nd, 3rd and 4th floors) | ||
| 10:00 am - 12:05 pm | 5 parallell sessions | ||
| Structured output, ILP and Sparsity (Mon 10:00 am, S1, 2nd floor) Session chair: Pedro Domingos | |||
| 10:00 am - 10:25 am | Paper #402: Accurate Max-margin Training for Structured Output Spaces. Sunita Sarawagi and Rahul Gupta. [Abstract] [Full paper] [Discussion] | ||
| 10:25 am - 10:50 am | Paper #279: Training Structural SVMs when Exact Inference is Intractable. Thomas Finley and Thorsten Joachims. [Abstract] [Full paper] [Discussion] | ||
| 10:50 am - 11:15 am | Paper #530: Discriminative Structure and Parameter Learning for Markov Logic Networks. Tuyen Huynh and Raymond Mooney. [Abstract] [Full paper] [Discussion] | ||
| 11:15 am - 11:40 am | Paper #237: Laplace Maximum Margin Markov Networks. Jun Zhu, Eric Xing, and Bo Zhang. [Abstract] [Full paper] [Discussion] | ||
| 11:40 am - 12:05 pm | Paper #503: Fast Estimation of Relational Pattern Coverage through Randomization and Maximum Likelihood. Ondrej Kuzelka and Filip Zelezny. [Abstract] [Full paper] [Discussion] | ||
| Kernel - Including Kernel Learning (Mon 10:00 am, S5, 3rd floor) Session chair: Nathan Srebro | |||
| 10:00 am - 10:25 am | Paper #158: Localized Multiple Kernel Learning. Mehmet Gonen and Ethem Alpaydin. [Abstract] [Full paper] [Discussion] | ||
| 10:25 am - 10:50 am | Paper #665: Composite Kernel Learning. Marie Szafranski, Yves Grandvalet, and Alain Rakotomamonjy. [Abstract] [Full paper] [Discussion] | ||
| 10:50 am - 11:15 am | Paper #531: Training SVM with Indefinite Kernels. Jianhui Chen and Jieping Ye. [Abstract] [Full paper] [Discussion] | ||
| 11:15 am - 11:40 am | Paper #449: Robust Matching and Recognition using Context-Dependent Kernels. Hichem Sahbi, Jean-Yves Audibert, Jaonary Rabarisoa, and Renaud Keriven. [Abstract] [Full paper] [Discussion] | ||
| 11:40 am - 12:05 pm | Paper #641: An RKHS for Multi-View Learning and Manifold Co-Regularization. Vikas Sindhwani and David Rosenberg. [Abstract] [Full paper] [Discussion] | ||
| Ranking and Classification with Sampling (Mon 10:00 am, S12, 3rd floor) Session chair: Ryan McDonald | |||
| 10:00 am - 10:25 am | Paper #489: Democratic Approximation of Lexicographic Preference Models. Fusun Yaman, Thomas Walsh, Michael Littman, and Marie desJardins. [Abstract] [Full paper] [Discussion] | ||
| 10:25 am - 10:50 am | Paper #343: Unsupervised Rank Aggregation with Distance-Based Models. Alexandre Klementiev, Dan Roth, and Kevin Small. [Abstract] [Full paper] [Discussion] | ||
| 10:50 am - 11:15 am | Paper #392: Learning Dissimilarities by Ranking: From SDP to QP. Hua Ouyang and Alexander Gray. [Abstract] [Full paper] [Discussion] | ||
| 11:15 am - 11:40 am | Paper #448: Optimizing Estimated Loss Reduction for Active Sampling in Rank Learning. Pinar Donmez and Jaime Carbonell. [Abstract] [Full paper] [Discussion] | ||
| 11:40 am - 12:05 pm | Paper #455: Bayes Optimal Classification for Decision Trees. Siegfried Nijssen. [Abstract] [Full paper] [Discussion] | ||
| Reinforcement Learning 3 (Mon 10:00 am, S13, 3rd floor) Session chair: Satinder Baveja | |||
| 10:00 am - 10:25 am | Paper #259: Non-Parametric Policy Gradients: A Unified Treatment of Propositional and Relational Domains. Kristian Kersting and Kurt Driessens. [Abstract] [Full paper] [Discussion] | ||
| 10:25 am - 10:50 am | Paper #488: Space-indexed Dynamic Programming: Learning to Follow Trajectories. J. Zico Kolter, Adam Coates, Andrew Ng, Yi Gu, and Charles DuHadway. [Abstract] [Full paper] [Discussion] | ||
| 10:50 am - 11:15 am | Paper #335: Privacy-Preserving Reinforcement Learning. Jun Sakuma, Shigenobu Kobayashi, and Rebecca Wright. [Abstract] [Full paper] [Discussion] | ||
| 11:15 am - 11:40 am | Paper #257: Learning All Optimal Policies with Multiple Criteria. Leon Barrett and Srinivas Narayanan. [Abstract] [Full paper] [Discussion] | ||
| Semi-supervised Learning - Embeddings and Transduction (Mon 10:00 am, SH, 4th floor) Session chair: Alex Smola | |||
| 10:00 am - 10:25 am | Paper #611: Semi-supervised Learning of Compact Document Representations with Deep Networks. Marc'Aurelio Ranzato and Martin Szummer. [Abstract] [Full paper] [Discussion] | ||
| 10:25 am - 10:50 am | Paper #382: Large Scale Manifold Transduction. Michael Karlen, Jason Weston, Ayse Erkan, and Ronan Collobert. [Abstract] [Full paper] [Discussion] | ||
| 10:50 am - 11:15 am | Paper #296: Graph Transduction via Alternating Minimization. Jun Wang, Tony Jebara, and Shih-Fu Chang. [Abstract] [Full paper] [Discussion] | ||
| 11:15 am - 11:40 am | Paper #254: Stability of Transductive Regression Algorithms. Corinna Cortes, Mehryar Mohri, Dmitry Pechyony, and Ashish Rastogi. [Abstract] [Full paper] [Discussion] | ||
| 11:40 am - 12:05 pm | Paper #383: On Multi-View Active Learning and the Combination with Semi-Supervised Learning. Wei Wang and Zhi-Hua Zhou. [Abstract] [Full paper] [Discussion] | ||
| 12:05 pm - 1:30 pm | Lunch (on your own) | ||
| 1:30 pm - 3:35 pm | 5 parallell sessions | ||
| Gaussian Processes (Mon 1:30 pm, S1, 2nd floor) Session chair: Neil Lawrence | |||
| 1:30 pm - 1:55 pm | Paper #151: Fast Gaussian Process Methods for Point Process Intensity Estimation. John Cunningham, Krishna Shenoy, and Maneesh Sahani. [Abstract] [Full paper] [Discussion] | ||
| 1:55 pm - 2:20 pm | Paper #241: Gaussian Process Product Models for Nonparametric Nonstationarity. Ryan Adams and Oliver Stegle. [Abstract] [Full paper] [Discussion] | ||
| 2:20 pm - 2:45 pm | Paper #599: Sparse Multiscale Gaussian Process Regression. Christian Walder, Kwang In Kim, and Bernhard Schoelkopf. [Abstract] [Full paper] [Discussion] | ||
| 2:45 pm - 3:10 pm | Paper #371: Topologically-Constrained Latent Variable Models. Raquel Urtasun, David Fleet, Andreas Geiger, Jovan Popovic, Trevor Darrell, and Neil Lawrence. [Abstract] [Full paper] [Discussion] | ||
| 3:10 pm - 3:35 pm | Paper #399: Bi-Level Path Following for Cross Validated Solution of Kernel Quantile Regression. Saharon Rosset. [Abstract] [Full paper] [Discussion] | ||
| Sequence Data (Mon 1:30 pm, S5, 3rd floor) Session chair: Chris Williams | |||
| 1:30 pm - 1:55 pm | Paper #278: A Distance Model for Rhythms. Jean-Francois Paiement, Yves Grandvalet, Samy Bengio, and Douglas Eck. [Abstract] [Full paper] [Discussion] | ||
| 1:55 pm - 2:20 pm | Paper #318: A Reproducing Kernel Hilbert Space Framework for Pairwise Time Series Distances. Zhengdong Lu, Todd K. Leen, Yonghong Huang, and Deniz Erdogmus. [Abstract] [Full paper] [Discussion] | ||
| 2:20 pm - 2:45 pm | Paper #440: Sequence Kernels for Predicting Protein Essentiality. Cyril Allauzen, Mehryar Mohri, and Ameet Talwalkar. [Abstract] [Full paper] [Discussion] | ||
| 2:45 pm - 3:10 pm | Paper #180: Local Likelihood Modeling of Temporal Text Streams. Guy Lebanon and Yang Zhao. [Abstract] [Full paper] [Discussion] | ||
| 3:10 pm - 3:35 pm | Paper #160: Causal Modelling Combining Instantaneous and Lagged Effects: an Identifiable Model Based on Non-Gaussianity. Aapo Hyvarinen, Shohei Shimizu, and Patrik Hoyer. [Abstract] [Full paper] [Discussion] | ||
| Feature Selection and Sparsity (Mon 1:30 pm, S12, 3rd floor) Session chair: Be Taskar | |||
| 1:30 pm - 1:55 pm | Paper #630: Detecting Statistical Interactions with Additive Groves of Trees. Daria Sorokina, Rich Caruana, Mirek Riedewald, and Daniel Fink. [Abstract] [Full paper] [Discussion] | ||
| 1:55 pm - 2:20 pm | Paper #574: Sparse Bayesian Nonparametric Regression. Francois Caron and Arnaud Doucet. [Abstract] [Full paper] [Discussion] | ||
| 2:20 pm - 2:45 pm | Paper #390: Bolasso: Model Consistent Lasso Estimation through the Bootstrap. Francis Bach. [Abstract] [Full paper] [Discussion] | ||
| 2:45 pm - 3:10 pm | Paper #113: The GroupLASSO for Generalized Linear Models: Uniqueness of Solutions and Efficient Algorithms. Volker Roth and Bernd Fischer. [Abstract] [Full paper] [Discussion] | ||
| 3:10 pm - 3:35 pm | Paper #323: On the Chance Accuracies of Large Collections of Classifiers. Mark Palatucci and Andrew Carlson. [Abstract] [Full paper] [Discussion] | ||
| Reinforcement Learning 4 - Active Learning (Mon 1:30 pm, S13, 3rd floor) Session chair: Doina Precup | |||
| 1:30 pm - 1:55 pm | Paper #290: Active Reinforcement Learning. Arkady Epshteyn, Adam Vogel, and Gerald DeJong. [Abstract] [Full paper] [Discussion] | ||
| 1:55 pm - 2:20 pm | Paper #487: Reinforcement Learning with Limited Reinforcement: Using Bayes Risk for Active Learning in POMDPs. Finale Doshi, Joelle Pineau, and Nicholas Roy. [Abstract] [Full paper] [Discussion] | ||
| 2:20 pm - 2:45 pm | Paper #490: The Many Faces of Optimism: a Unifying Approach. Istvan Szita and Andras Lorincz. [Abstract] [Full paper] [Discussion] | ||
| 2:45 pm - 3:10 pm | Paper #479: Transfer of Samples in Batch Reinforcement Learning. Alessandro Lazaric, Marcello Restelli, and Andrea Bonarini. [Abstract] [Full paper] [Discussion] | ||
| 3:10 pm - 3:35 pm | Paper #519: Exploration Scavenging. John Langford, Alexander Strehl, and Jennifer Wortman. [Abstract] [Full paper] [Discussion] | ||
| Semi-supervised Clustering and Classification (Mon 1:30 pm, SH, 4th floor) Session chair: Andrew McCallum | |||
| 1:30 pm - 1:55 pm | Paper #337: Estimating Labels from Label Proportions. Novi Quadrianto, Alex Smola, Tiberio Caetano, and Quoc Viet Le. [Abstract] [Full paper] [Discussion] | ||
| 1:55 pm - 2:20 pm | Paper #432: Self-taught Clustering. Wenyuan Dai, Qiang Yang, Gui-Rong Xue, and Yong Yu. [Abstract] [Full paper] [Discussion] | ||
| 2:20 pm - 2:45 pm | Paper #172: Spectral Clustering with Inconsistent Advice. Tom Coleman, James Saunderson, and Anthony Wirth. [Abstract] [Full paper] [Discussion] | ||
| 2:45 pm - 3:10 pm | Paper #145: Pairwise Constraint Propagation by Semidefinite Programming for Semi-Supervised Classification. Zhenguo Li, Jianzhuang Liu, and Xiaoou Tang. [Abstract] [Full paper] [Discussion] | ||
| 3:10 pm - 3:35 pm | Paper #528: The Asymptotics of Semi-Supervised Learning in Discriminative Probabilistic Models. Nataliya Sokolovska, Olivier Cappé, and François Yvon. [Abstract] [Full paper] [Discussion] | ||
| 3:35 pm - 4:05 pm | Coffee Break (2nd, 3rd and 4th floors) | ||
| 4:05 pm - 5:05 pm | Invited talk: Michael Collins, MIT: Structured Prediction Problems in Natural Language Processing (S1, 2nd floor) | ||
| 5:05 pm - 5:45 pm | Break, leave for boats | ||
| 5:45 pm - 6:45 pm | Boats leave to Suomenlinna from the Market Square | ||
| 7:00 pm - 10:30 pm | Conference Banquet | ||
Tuesday, July 8, 2008 | |||
| Breakfast in hotel | |||
| 8:00 am - | Registration (1st [ground] floor) | ||
| 8:30 am - 10:10 am | 5 parallell sessions | ||
| Discriminative vs Generative, and Energy-Based Learning (Tue 8:30 am, S1, 2nd floor) Session chair: Andrew Ng | |||
| 8:30 am - 8:55 am | Paper #415: Discriminative Parameter Learning for Bayesian Networks. Jiang Su, Harry Zhang, Charles X. Ling, and Stan Matwin. [Abstract] [Full paper] [Discussion] | ||
| 8:55 am - 9:20 am | Paper #601: Classification using Discriminative Restricted Boltzmann Machines. Hugo Larochelle and Yoshua Bengio. [Abstract] [Full paper] [Discussion] | ||
| 9:20 am - 9:45 am | Paper #573: On the Quantitative Analysis of Deep Belief Networks. Ruslan Salakhutdinov and Iain Murray. [Abstract] [Full paper] [Discussion] | ||
| 9:45 am - 10:10 am | Paper #638: Training Restricted Boltzmann Machines using Approximations to the Likelihood Gradient. Tijmen Tieleman. [Abstract] [Full paper] [Discussion] | ||
| Boosting (Tue 8:30 am, S5, 3rd floor) Session chair: William Cohen | |||
| 8:30 am - 8:55 am | Paper #676: ManifoldBoost: Stagewise Function Approximation for Fully-, Semi- and Un-supervised Learning. Nicolas Loeff, David Forsyth, and Deepak Ramachandran. [Abstract] [Full paper] [Discussion] | ||
| 8:55 am - 9:20 am | Paper #331: Boosting with Incomplete Information. Gholamreza Haffari, Yang Wang, Shaojun Wang, Greg Mori, and Feng Jiao. [Abstract] [Full paper] [Discussion] | ||
| 9:20 am - 9:45 am | Paper #362: Maximum Likelihood Rule Ensembles. Wojciech Kotlowski, Krzysztof Dembczynski, and Roman Slowinski. [Abstract] [Full paper] [Discussion] | ||
| 9:45 am - 10:10 am | Paper #258: Random Classification Noise Defeats All Convex Potential Boosters. Philip M. Long and Rocco A. Servedio. [Abstract] [Full paper] [Discussion] | ||
| Compressed Sensing and Projections (Tue 8:30 am, S12, 3rd floor) Session chair: Martin Wainwright | |||
| 8:30 am - 8:55 am | Paper #121: Autonomous Geometric Precision Error Estimation in Low-level Computer Vision Tasks. Andrés Corrada-Emmanuel and Howard Schultz. [Abstract] [Full paper] [Discussion] | ||
| 8:55 am - 9:20 am | Paper #209: Multi-Task Compressive Sensing with Dirichlet Process Priors. Yuting Qi, Dehong Liu, David Dunson, and Lawrence Carin. [Abstract] [Full paper] [Discussion] | ||
| 9:20 am - 9:45 am | Paper #459: Compressed Sensing and Bayesian Experimental Design. Matthias Seeger and Hannes Nickisch. [Abstract] [Full paper] [Discussion] | ||
| 9:45 am - 10:10 am | Paper #361: Efficient Projections onto the L1-Ball for Learning in High Dimensions. John Duchi, Shai Shalev-Shwartz, Yoram Singer, and Tushar Chandra. [Abstract] [Full paper] [Discussion] | ||
| Reinforcement Learning 5 (Tue 8:30 am, S13, 3rd floor) Session chair: Csaba Szepesvari | |||
| 8:30 am - 8:55 am | Paper #581: An Analysis of Linear Models, Linear Value-Function Approximation, and Feature Selection for Reinforcement Learning. Ronald Parr, Lihong Li, Gavin Taylor, Christopher Painter-Wakefield, and Michael Littman. [Abstract] [Full paper] [Discussion] | ||
| 8:55 am - 9:20 am | Paper #652: An Analysis of Reinforcement Learning with Function Approximation. Francisco Melo, Sean Meyn, and Isabel Ribeiro. [Abstract] [Full paper] [Discussion] | ||
| 9:20 am - 9:45 am | Paper #645: Apprenticeship Learning Using Linear Programming. Umar Syed, Michael Bowling, and Robert Schapire. [Abstract] [Full paper] [Discussion] | ||
| 9:45 am - 10:10 am | Paper #111: Preconditioned Temporal Difference Learning. Hengshuai Yao and Zhi-Qiang Liu. [Abstract] [Full paper] [Discussion] | ||
| Ranking and IR (Tue 8:30 am, SH, 4th floor) Session chair: Joaquin Quiñonero | |||
| 8:30 am - 8:50 am | Paper #167: Listwise Approach to Learning to Rank - Theory and Algorithm. Fen Xia, Tie-Yan Liu, Jue Wang, Wensheng Zhang, and Hang Li. [Abstract] [Full paper] [Discussion] | ||
| 8:55 am - 9:20 am | Paper #179: Query-Level Stability and Generalization in Learning to Rank. Yanyan Lan, Tie-Yan Liu, Tao Qin, Zhiming Ma, and Hang Li. [Abstract] [Full paper] [Discussion] | ||
| 9:20 am - 9:45 am | Paper #470: Predicting Diverse Subsets Using Structural SVMs. Yisong Yue and Thorsten Joachims. [Abstract] [Full paper] [Discussion] | ||
| 9:45 am - 10:10 am | Paper #264: Learning Diverse Rankings with Multi-Armed Bandits. Filip Radlinski, Robert Kleinberg, and Thorsten Joachims. [Abstract] [Full paper] [Discussion] | ||
| 10:10 am - 10:40 am | Coffee Break (2nd, 3rd and 4th floors) | ||
| 10:40 am - 12:20 pm | 5 parallell sessions | ||
| Topic Models (Tue 10:40 am, S1, 2nd floor Session chair: Wray Buntine | |||
| 10:40 am - 11:05 am | Paper #562: mStruct: A New Admixture Model for Inference of Population Structure in Light of Both Genetic Admixing and Allele Mutations. Suyash Shringarpure and Eric Xing. [Abstract] [Full paper] [Discussion] | ||
| 11:05 am - 11:30 am | Paper #419: Memory Bounded Inference in Topic Models. Ryan Gomes, Max Welling, and Pietro Perona. [Abstract] [Full paper] [Discussion] | ||
| 11:30 am - 11:55 am | Paper #667: Nonnegative Matrix Factorization via Rank-One Downdate. Michael Biggs, Ali Ghodsi, and Stephen Vavasis. [Abstract] [Full paper] [Discussion] | ||
| 11:55 am - 12:20 pm | Paper #129: Dirichlet Component Analysis: Feature Extraction for Compositional Data. Hua-Yan Wang, Qiang Yang, Hong Qin, and Hongbin Zha. [Abstract] [Full paper] [Discussion] | ||
| Embeddings 1 (Tue 10:40 am, S5, 3rd floor) Session chair: Neil Lawrence | |||
| 10:40 am - 11:05 am | Paper #163: Uncorrelated Multilinear Principal Component Analysis through Successive Variance Maximization. Haiping Lu, Konstantinos Plataniotis, and Anastasios Venetsanopoulos. [Abstract] [Full paper] [Discussion] | ||
| 11:05 am - 11:30 am | Paper #484: Expectation-Maximization for Sparse and Non-Negative PCA. Christian David Sigg and Joachim M. Buhmann. [Abstract] [Full paper] [Discussion] | ||
| 11:30 am - 11:55 am | Paper #551: ICA and ISA Using Schweizer-Wolff Measure of Dependence. Sergey Kirshner and Barnabás Póczos. [Abstract] [Full paper] [Discussion] | ||
| 11:55 am - 12:20 pm | Paper #600: Bayesian Probabilistic Matrix Factorization using Markov Chain Monte Carlo. Ruslan Salakhutdinov and Andriy Mnih. [Abstract] [Full paper] [Discussion] | ||
| Classification with Sampling, Costs (Tue 10:40 am, S12, 3rd floor) Session chair: Carla Brodley | |||
| 10:40 am - 11:05 am | Paper #523: Empirical Bernstein Stopping. Volodymyr Mnih, Csaba Szepesvari, and Jean-Yves Audibert. [Abstract] [Full paper] [Discussion] | ||
| 11:05 am - 11:30 am | Paper #614: Pointwise Exact Bootstrap Distributions of Cost Curves. Charles Dugas and David Gadoury. [Abstract] [Full paper] [Discussion] | ||
| 11:30 am - 11:55 am | Paper #632: An Empirical Evaluation of Supervised Learning in High Dimensions. Rich Caruana, Nikos Karampatziakis, Ainur Yessenalina [Abstract] [Full paper] [Discussion] | ||
| 11:55 am - 12:20 pm | Paper #150: Cost-Sensitive Multi-class Classification from Probability Estimates. Deirdre O'Brien, Maya Gupta, and Robert Gray. [Abstract] [Full paper] [Discussion] | ||
| Reinforcement Learning 6 (Tue 10:40 am, S13, 3rd floor) Session chair: Doina Precup | |||
| 10:40 am - 11:05 am | Paper #458: Automatic Discovery and Transfer of MAXQ Hierarchies. Neville Mehta, Soumya Ray, Prasad Tadepalli, and Thomas Dietterich. [Abstract] [Full paper] [Discussion] | ||
| 11:05 am - 11:30 am | Paper #564: Sample-Based Learning and Search with Permanent and Transient Memories. David Silver, Richard Sutton, and Martin Mueller. [Abstract] [Full paper] [Discussion] | ||
| 11:30 am - 11:55 am | Paper #197: Efficiently Learning Linear-Linear Exponential Family Predictive Representations of State. David Wingate and Satinder Singh. [Abstract] [Full paper] [Discussion] | ||
| 11:55 am - 12:20 pm | Paper #429: A Semi-parametric Statistical Approach to Model-free Policy Evaluation. Tsuyoshi Ueno, Motoaki Kawanabe, Takeshi Mori, Shin-Ichi Maeda, and Shin Ishii. [Abstract] [Full paper] [Discussion] | ||
| Online Learning (Tue 10:40 am, SH, 4th floor) Session chair: Manfred Warmuth | |||
| 10:40 am - 11:05 am | Paper #367: Rank Minimization via Online Learning. Raghu Meka, Prateek Jain, Constantine Caramanis, and Inderjit Dhillon. [Abstract] [Full paper] [Discussion] | ||
| 11:05 am - 11:30 am | Paper #322: Confidence-Weighted Linear Classification. Mark Dredze, Koby Crammer, and Fernando Pereira. [Abstract] [Full paper] [Discussion] | ||
| 11:30 am - 11:55 am | Paper #355: The Projectron: a Bounded Kernel-Based Perceptron. Francesco Orabona, Joseph Keshet, and Barbara Caputo. [Abstract] [Full paper] [Discussion] | ||
| 11:55 am - 12:20 pm | Paper #511: Efficient Bandit Algorithms for Online Multiclass Prediction. Sham M. Kakade, Shai Shalev-Shwartz, and Ambuj Tewari. [Abstract] [Full paper] [Discussion] | ||
| 12:20 pm - 2:00 pm | Lunch (on your own) | ||
| 2:00 pm - 4:05 pm | 5 parallell sessions | ||
| NLP (Tue 2:00 pm, S1, 2nd floor) Session chair: Ryan McDonald | |||
| 2:00 pm - 2:25 pm | Paper #304: Learning to Sportscast: A Test of Grounded Language Acquisition. David Chen and Raymond Mooney. [Abstract] [Full paper] [Discussion] | ||
| 2:25 pm - 2:50 pm | Paper #391: A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning. Ronan Collobert and Jason Weston. [Abstract] [Full paper] [Discussion] | ||
| 2:50 pm - 3:15 pm | Paper #398: Modified MMI/MPE: a Direct Evaluation of the Margin in Speech Recognition. Georg Heigold, Thomas Deselaers, Ralf Schlueter, and Hermann Ney. [Abstract] [Full paper] [Discussion] | ||
| 3:15 pm - 3:40 pm | Paper #311: Fully Distributed EM for Very Large Datasets. Jason Wolfe, Aria Haghighi, and Dan Klein. [Abstract] [Full paper] [Discussion] | ||
| 3.40 pm - 4:05 pm | Paper #673: Structure Compilation: Trading Structure for Features. Percy Liang, Hal Daume, and Dan Klein. [Abstract] [Full paper] [Discussion] | ||
| Multiple Instance Learning and Learning with Missing Features, Categorical Features (Tue 2:00 pm, S5, 3rd floor) Session chair: Tom Dietterich | |||
| 2:00 pm - 2:25 pm | Paper #130: Adaptive p-Posterior Mixture-Model Kernels for Multiple Instance Learning. Hua-Yan Wang, Qiang Yang, and Hongbin Zha. [Abstract] [Full paper] [Discussion] | ||
| 2:25 pm - 2:50 pm | Paper #552: Multiple Instance Ranking. Charles Bergeron, Jed Zaretzki, Curt Breneman, and Kristin Bennett. [Abstract] [Full paper] [Discussion] | ||
| 2:50 pm - 3:15 pm | Paper #587: Bayesian Multiple Instance Learning: Automatic Feature Selection and Inductive Transfer. Vikas Raykar, Balaji Krishnapuram, Jinbo Bi, Murat Dundar, and R. Bharat Rao. [Abstract] [Full paper] [Discussion] | ||
| 3:15 pm - 3:40 pm | Paper #202: Learning to Classify with Missing and Corrupted Features. Ofer Dekel and Ohad Shamir. [Abstract] [Full paper] [Discussion] | ||
| 3:40 pm - 4:05 pm | Paper #536: Multi-Classification by Categorical Features via Clustering. Yevgeny Seldin and Naftali Tishby. [Abstract] [Full paper] [Discussion] | ||
| Embeddings 2 (Tue 2:00 pm, S12, 3rd floor) Session chair: Lawrence Saul | |||
| 2:00 pm - 2:25 pm | Paper #270: A Least Squares Formulation for Canonical Correlation Analysis. Liang Sun, Shuiwang Ji, and Jieping Ye. [Abstract] [Full paper] [Discussion] | ||
| 2:25 pm - 2:50 pm | Paper #668: Closed-form Supervised Dimensionality Reduction with Generalized Linear Models. Irina Rish, Genady Grabarnilk, Guillermo Cecchi, Francisco Pereira, and Geoffrey J. Gordon. [Abstract] [Full paper] [Discussion] | ||
| 2:50 pm - 3:15 pm | Paper #312: Grassmann Discriminant Analysis: a Unifying View on Subspace-Based Learning. Jihun Hamm and Daniel Lee. [Abstract] [Full paper] [Discussion] | ||
| 3:15 pm - 3:40 pm | Paper #582: Metric Embedding for Kernel Classification Rules. Bharath Sriperumbudur, Omer Lang, and Gert Lanckriet. [Abstract] [Full paper] [Discussion] | ||
| 3:40 pm - 4:05 pm | Paper #592: Extracting and Composing Robust Features with Denoising Autoencoders. Pascal Vincent, Hugo Larochelle, Yoshua Bengio, and Pierre-Antoine Manzagol. [Abstract] [Full paper] [Discussion] | ||
| Transfer Learning and Games (Tue 2:00 pm, S13, 3rd floor) Session chair: Andrew Ng | |||
| 2:00 pm - 2:25 pm | Paper #412: Learning to Learn Implicit Queries from Gaze Patterns. Kai Puolamäki, Antti Ajanki, and Samuel Kaski. [Abstract] [Full paper] [Discussion] | ||
| 2:25 pm - 2:50 pm | Paper #520: Multi-Task Learning for HIV Therapy Screening. Steffen Bickel, Jasmina Bogojeska, Thomas Lengauer, and Tobias Scheffer. [Abstract] [Full paper] [Discussion] | ||
| 2:50 pm - 3:15 pm | Paper #229: Manifold Alignment using Procrustes Analysis. Chang Wang and Sridhar Mahadevan. [Abstract] [Full paper] [Discussion] | ||
| 3:15 pm - 3:40 pm | Paper #542: No-Regret Learning in Convex Games. Geoffrey J. Gordon, Amy Greenwald, and Casey Marks. [Abstract] [Full paper] [Discussion] | ||
| 3:40 pm - 4:05 pm | Paper #655: Strategy Evaluation in Extensive Games with Importance Sampling. Michael Bowling, Michael Johanson, Neil Burch, and Duane Szafron. [Abstract] [Full paper] [Discussion] | ||
| Kernels - Including Scalability (Tue 2:00 pm, SH, 4th floor) Session chair: Shai Shalev-Shwartz | |||
| 2:00 pm - 2:25 pm | Paper #166: A Dual Coordinate Descent Method for Large-scale Linear SVM. Cho-Jui Hsieh, Kai-Wei Chang, Chih-Jen Lin, S. Sathiya Keerthi, and S. Sundararajan. [Abstract] [Full paper] [Discussion] | ||
| 2:25 pm - 2:50 pm | Paper #411: Optimized Cutting Plane Algorithm for Support Vector Machines. Vojtech Franc and Soeren Sonnenburg. [Abstract] [Full paper] [Discussion] | ||
| 2:50 pm - 3:15 pm | Paper #491: Fast Support Vector Machine Training and Classification on Graphics Processors. Bryan Catanzaro, Narayanan Sundaram, and Kurt Keutzer. [Abstract] [Full paper] [Discussion] | ||
| 3:15 pm - 3:40 pm | Paper #476: Improved Nystrom Low-Rank Approximation and Error Analysis. Kai Zhang, Ivor Tsang, and James Kwok. [Abstract] [Full paper] [Discussion] | ||
| 3:40 pm - 4:05 pm | Paper #513: Polyhedral Classifier for Target Detection A Case Study: Colorectal Cancer. Murat Dundar, Matthias Wolf, Sarang Lakare, Marcos Salganicoff, and Vikas C. Raykar. [Abstract] [Full paper] [Discussion] | ||
| 4:05 pm - 4:35 pm | Coffee Break (2nd, 3rd and 4th floors) | ||
| 4:35 pm - 5:35 pm | Invited Talk: Andrew Ng, Stanford University: STAIR: The STanford Artificial Intelligence Robot project (S1, 2nd floor) | ||
| 5:40 pm - 6:30 pm | Business Meeting (S1, 2nd floor) | ||
| 6:00 pm - 8:30 pm | Poster Session II (2nd & 3rd floors, with snacks): Posters from sessions Feature selection and sparsity (Mon 1:30 pm) upto and including Kernels - Including scalability (Tue 2:00 pm). | ||