The 17th International Conference on Algorithmic Learning Theory Barcelona, Spain October 7-10, 2006

Time Schedule The conference starts on Saturday, October 7th, with two tutorials, scheduled as follows: 10:00-13:30: Morning Tutorial Michael May: Geographic and Spatial Data Mining 13:30-15:00: Lunch Break 15:00-18:30: Afternoon Tutorial Luis Torgo: Using R for Data Mining and Scientific Discovery 18:30-20:00: Steering Committee Meeting The table below presents the schedule for the other three days of the conference. Note that further info on tutorials and invited talks can be found on the Tutorial page. Time Sunday, 8 October Monday, 9 October Tuesday, 10 October 10:00-11:00 Morning Invited Talks Andrew Ng Reinforcement Learning and Apprenticeship Learning for Robotic Control Ulrich Simon The Usage of the Spectral Norm in Learning Theory: Some Selected Topics Gunnar Rätsch The Solution of Semi-Infinite Linear Programs using Boosting-like Methods 11:00-11:30 Coffee Break 11:30-12:20 Query Learning Online Learning Reinforcement Learning Nader H. Bshouty and Ehab Wattad On Exact Learning Halfspaces with Random Consistent Hypothesis Oracle Gold Award Lecture Alp Atıcı and Rocco A. Servedio Learning Unions of ω(1)$-Dimensional Rectangles Nader H. Bshouty and Iddo Bentov On Exact Learning from Random Walk Eyal Even-Dar, Michael Kearns and Jennifer Wortman Risk-Sensitive Online Learning Daniil Ryabko and Marcus Hutter Asymptotic Learnability of Reinforcement Problems with Arbitrary Dependence Takeshi Shibata, Ryo Yoshinaka and Takashi Chikayama Probabilistic Generalization of Simple Grammars and Its Application to Reinforcement Learning 12:20-12:30 Short Break 12:30-13:20 Applications of Query Learning Predicting with Experts Statistical Learning Matti Kääriäinen Active Learning in the Non-realizable Case Jorge Castro How Many Query Superpositions Are Needed to Learn? Vladimir Vovk Leading Strategies in Competitive On-Line Learning Chamy Allenberg, Peter Auer, Laszlo Györfi and György Ottucsák Hannan Consistency in On-Line Learning in Case of Unbounded Losses under Partial Monitoring Andreas Maurer Unsupervised Slow Subspace-Learning from Stationary Processes Atsuyoshi Nakamura Learning-Related Complexity of Linear Ranking Functions 13:30-15:00 Lunch Break 15:00-16:00 Afternoon Invited Talks Carole Goble Putting Semantics into e-Science and the Grid Padhraic Smyth Data-Driven Discovery using Probabilistic Hidden Variable Models Adjorn 16:00-16:10 Short Break 16:10-17:25 Complexity of Learning Algorithmic Forecasting Frank J. Balbach and Thomas Zeugmann Teaching Memoryless Randomized Learners without Feedback Stephen Fenner and William Gasarch The Complexity of Learning SUBSEQ(A) Matthew de Brecht and Akihiro Yamamoto Mind Change Complexity of Inferring Unbounded Unions of Pattern Languages From Positive Data Marcus Hutter General Discounting versus Average Reward Jan Poland The Missing Consistency Theorem for Bayesian Learning: Stochastic Model Selection Shane Legg Is there an Elegant Universal Theory of Prediction? 17:25-17:55 Coffee Break 17:55-19:10 Inductive Inference Boosting, Support Vector Machines and Kernel Methods Sanjay Jain and Efim Kinber Learning and Extending Sublanguages Sanjay Jain and Efim Kinber Iterative Learning from Positive Data and Negative Counterexamples Sanjay Jain, Steffen Lange and Sandra Zilles Towards a Better Understanding of Incremental Learning Leonid Kontorovich, Corinna Cortes, Mehryar Mohri Learning Linearly Separable Languages Kohei Hatano Smooth Boosting Using an Information-Based Criterion Hsuan-Tien Lin and Ling Li Large-Margin Thresholded Ensembles for Ordinal Regression: Theory and Practice 20:00- Business Meeting Banquet