COLT 2011 - Program

July 8, Friday

17:00 - 19:00	Registration
19:00 - 20:00	Welcome reception at Danubius Hotel Flamenco

July 9, Saturday

09:00 – 10:15	Recommendation Systems and Matrix Estimation
10:15 – 10:45	Coffee
10:45 – 11:45	Invited talk
11:45 – 12:35	Sparsity
12:35 – 14:35	Lunch break
14:35 – 16:15	Computation and Learning
16:15 – 16:45	Coffee
16:45 – 17:10	Privacy
17:10 – 18:40	Open problems session
20.30 –	Business meeting

July 10, Sunday

09:00 – 10:40	Learnability
10:40 – 11:10	Coffee
11:10 – 12:50	Statistical Estimation
12:50 – 14:50	Lunch break
14:50 – 16:05	Online Learning, approachability, and calibration
16:05 – 16:35	Coffee
16:35 – 17:25	Control and Reinforcement Learning
17:25 – 18:25	Impromptu
19:00 – 21:00	Banquet at Hemingway Restaurant (Kosztolányi Dezső tér 2 -near the lake)

July 11, Monday

09:00 – 10:40	Bandits
10:40 – 11:10	Coffee
11:10 – 12:10	Invited talk
12:10 – 13:00	Optimization
13:00 – 15:00	Lunch break
15:00 – 16:15	Games
16:15 – 16:45	Coffee
16:45 – 18:25	Aggregation Methods and MDL

July 9, Saturday

09:00 – 10:15	Recommendation Systems and Matrix Estimation Ohad Shamir and Shai Shalev-Shwartz Collaborative Filtering with the Trace Norm: Learning, Bounding, and Transducing Rina Foygel and Nathan Srebro Concentration-Based Guarantees for Low-Rank Matrix Reconstruction Cynthia Rudin, Ansaf Salleb-Aouissi, Eugene Kogan and David Madigan Sequential Event Prediction with Association Rules
10:15 – 10:45	Coffee
10:45 – 11:45	Invited talk David Hand Learning in the real world
11:45 – 12:35	Sparsity Arnak Dalalyan and Laëtitia Comminges Tight conditions for consistent variable selection in high dimensional nonparametric regression Sébastien Gerchinovitz Sparsity regret bounds for individual sequences in online linear regression
12:35 – 14:35	Lunch break
14:35 – 16:15	Computation and Learning Vitaly Feldman Distribution-Independent Evolvability of Linear Threshold Functions Vitaly Feldman, Homin K. Lee and Rocco Servedio Lower Bounds and Hardness Amplification for Learning Shallow Monotone Formulas Alekh Agarwal, John Duchi, Peter Bartlett and Clement Levrard Oracle inequalities for computationally budgeted model selection Michael Kallweit and Hans Simon A Close Look to Margin Complexity and Related Parameters
16:15 – 16:45	Coffee
16:45 – 17:10	Privacy Kamalika Chaudhuri and Daniel Hsu Sample Complexity Bounds for Differentially Private Learning
17:10 – 18:40	Open problems session Elad Hazan and Satyen Kale A simple multi-armed bandit algorithm with optimal variation-bounded regret Aleksandrs Slivkins Monotone multi-armed bandit allocations Loizos Michael Missing information impediments to learnability Jacob Abernethy and Shie Mannor Does an efficient calibrated forecasting strategy exist? Peter Grünwald and Wojciech Kotłowski Bounds on individual risk for log-loss predictors Wojciech Kotłowski and Manfred Warmuth Minimax algorithm for learning rotations
20.30 -	Business meeting

July 10, Sunday

09:00 – 10:40	Learnability Amit Daniely, Sivan Sabato, Shai Ben-David and Shai Shalev-Shwartz Multiclass Learnability and the ERM principle Daniel Vainsencher, Shie Mannor and Alfred Bruckstein The Sample Complexity of Dictionary Learning Liu Yang, Steve Hanneke and Jaime Carbonell Identifiability of Priors from Bounded Sample Sizes with Applications to Transfer Learning Wei Gao and Zhi-Hua Zhou On the Consistency of Multi-Label Learning
10:40 – 11:10	Coffee
11:10 – 12:50	Statistical Estimation Jayadev Acharya, Hirakendu Das, Ashkan Jafarpour, Alon Orlitsky and Shengjun Pan Competitive Closeness Testing Philippe Rigollet and Xin Tong Neyman-Pearson classification under a strict constraint Ingo Steinwart Adaptive Density Level Set Clustering Ping Li and Cun-Hui Zhang A New Algorithm for Compressed Counting with Applications in Shannon Entropy Estimation in Dynamic Data
12:50 – 14:50	Lunch break
14:50 – 16:05	Online Learning, approachability, and calibration Jacob Abernethy, Peter Bartlett and Elad Hazan Blackwell Approachability and No-Regret Learning are Equivalent Alexander Rakhlin, Karthik Sridharan and Ambuj Tewari Online Learning: Beyond Regret Dean Foster, Alexander Rakhlin, Karthik Sridharan and Ambuj Tewari Complexity-Based Approach to Calibration with Checking Rules
16:05 – 16:35	Coffee
16:35 – 17:25	Control and Reinforcement Learning Istvan Szita and Csaba Szepesvári Agnostic KWIK learning and efficient approximate reinforcement learning Yasin Abbasi-Yadkori and Csaba Szepesvári Regret Bounds for the Adaptive Control of Linear Quadratic Systems
17:25 – 18:25	Inpromptu
19:00 – 22:00	Banquet at Hemingway Restaurant (Kosztolányi Dezső tér 2 -near the lake)

July 11, Monday

09:00 – 10:40	Bandits Aurélien Garivier and Olivier Cappé The KL-UCB Algorithm for Bounded Stochastic Bandits and Beyond Odalric-Ambrym Maillard, Gilles Stoltz and Remi Munos A Finite-Time Analysis of Multi-armed Bandits Problems with Kullback-Leibler Divergences Kareem Amin, Michael Kearns and Umar Syed Bandits, Query Learning, and the Haystack Dimension Aleksandrs Slivkins Contextual Bandits with Similarity Information
10:40 – 11:10	Coffee
11:10 – 12:10	Invited talk Bill Freeman Where machine vision needs help from machine learning
12:10 – 13:00	Optimization Indraneel Mukherjee, Cynthia Rudin and Robert Schapire The Rate of Convergence of AdaBoost Elad Hazan and Satyen Kale Beyond the regret minimization barrier: an optimal algorithm for stochastic strongly-convex optimization
13:00 – 15:00	Lunch break
15:00 – 16:15	Games Jean-Yves Audibert, Sébastien Bubeck and Gábor Lugosi Minimax Policies for Combinatorial Prediction Games Shie Mannor, Vianney Perchet and Gilles Stoltz Robust approachability and regret minimization in games with partial monitoring Gábor Bartók, Dávid Pál and Csaba Szepesvári Minimax Regret of Finite Partial-Monitoring Games in Stochastic Environments
16:15 – 16:45	Coffee
16:45 – 18:25	Aggregation Methods and MDL Arnak Dalalyan and Joseph Salmon Optimal aggregation of affine estimators Tim Van Erven, Mark Reid and Robert Williamson Mixability is Bayes Risk Curvature Relative to Log Loss Peter Grünwald Safe Learning: bridging the gap between Bayes, MDL and statistical learning theory via empirical convexity Wojciech Kotlowski and Peter Grünwald Maximum Likelihood vs. Sequential Normalized Maximum Likelihood in On-line Density Estimation