Algorithmic Learning Theory: 17th International Conference, ALT 2006, Barcelona, Spain, October 7-10, 2006. Proceedings

Jose L. Balcázar, Philip M. Long, Frank Stephan (auth.), José L. Balcázar, Philip M. Long, Frank Stephan (eds.)9783540466499, 3540466495

This book constitutes the refereed proceedings of the 17th International Conference on Algorithmic Learning Theory, ALT 2006, held in Barcelona, Spain in October 2006, colocated with the 9th International Conference on Discovery Science, DS 2006.

The 24 revised full papers presented together with the abstracts of five invited papers were carefully reviewed and selected from 53 submissions. The papers are dedicated to the theoretical foundations of machine learning. They address topics such as query models, on-line learning, inductive inference, algorithmic forecasting, boosting, support vector machines, kernel methods, reinforcement learning, and statistical learning models.

---

Table of contents :
Front Matter….Pages –
Editors’ Introduction….Pages 1-9
Solving Semi-infinite Linear Programs Using Boosting-Like Methods….Pages 10-11
e-Science and the Semantic Web: A Symbiotic Relationship….Pages 12-12
Spectral Norm in Learning Theory: Some Selected Topics….Pages 13-27
Data-Driven Discovery Using Probabilistic Hidden Variable Models….Pages 28-28
Reinforcement Learning and Apprenticeship Learning for Robotic Control….Pages 29-31
Learning Unions of ω (1)-Dimensional Rectangles….Pages 32-47
On Exact Learning Halfspaces with Random Consistent Hypothesis Oracle….Pages 48-62
Active Learning in the Non-realizable Case….Pages 63-77
How Many Query Superpositions Are Needed to Learn?….Pages 78-92
Teaching Memoryless Randomized Learners Without Feedback….Pages 93-108
The Complexity of Learning SUBSEQ ( A )….Pages 109-123
Mind Change Complexity of Inferring Unbounded Unions of Pattern Languages from Positive Data….Pages 124-138
Learning and Extending Sublanguages….Pages 139-153
Iterative Learning from Positive Data and Negative Counterexamples….Pages 154-168
Towards a Better Understanding of Incremental Learning….Pages 169-183
On Exact Learning from Random Walk….Pages 184-198
Risk-Sensitive Online Learning….Pages 199-213
Leading Strategies in Competitive On-Line Prediction….Pages 214-228
Hannan Consistency in On-Line Learning in Case of Unbounded Losses Under Partial Monitoring….Pages 229-243
General Discounting Versus Average Reward….Pages 244-258
The Missing Consistency Theorem for Bayesian Learning: Stochastic Model Selection….Pages 259-273
Is There an Elegant Universal Theory of Prediction?….Pages 274-287
Learning Linearly Separable Languages….Pages 288-303
Smooth Boosting Using an Information-Based Criterion….Pages 304-318
Large-Margin Thresholded Ensembles for Ordinal Regression: Theory and Practice….Pages 319-333
Asymptotic Learnability of Reinforcement Problems with Arbitrary Dependence….Pages 334-347
Probabilistic Generalization of Simple Grammars and Its Application to Reinforcement Learning….Pages 348-362
Unsupervised Slow Subspace-Learning from Stationary Processes….Pages 363-377
Learning-Related Complexity of Linear Ranking Functions….Pages 378-392
Back Matter….Pages –