Algorithmic Learning Theory

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.

Inhalt

Editors' Introduction.- Editors' Introduction.- Invited Contributions.- Solving Semi-infinite Linear Programs Using Boosting-Like Methods.- e-Science and the Semantic Web: A Symbiotic Relationship.- Spectral Norm in Learning Theory: Some Selected Topics.- Data-Driven Discovery Using Probabilistic Hidden Variable Models.- Reinforcement Learning and Apprenticeship Learning for Robotic Control.- Regular Contributions.- Learning Unions of ?(1)-Dimensional Rectangles.- On Exact Learning Halfspaces with Random Consistent Hypothesis Oracle.- Active Learning in the Non-realizable Case.- How Many Query Superpositions Are Needed to Learn?.- Teaching Memoryless Randomized Learners Without Feedback.- The Complexity of Learning SUBSEQ (A).- Mind Change Complexity of Inferring Unbounded Unions of Pattern Languages from Positive Data.- Learning and Extending Sublanguages.- Iterative Learning from Positive Data and Negative Counterexamples.- Towards a Better Understanding of Incremental Learning.- On Exact Learning from Random Walk.- Risk-Sensitive Online Learning.- Leading Strategies in Competitive On-Line Prediction.- Hannan Consistency in On-Line Learning in Case of Unbounded Losses Under Partial Monitoring.- General Discounting Versus Average Reward.- The Missing Consistency Theorem for Bayesian Learning: Stochastic Model Selection.- Is There an Elegant Universal Theory of Prediction?.- Learning Linearly Separable Languages.- Smooth Boosting Using an Information-Based Criterion.- Large-Margin Thresholded Ensembles for Ordinal Regression: Theory and Practice.- Asymptotic Learnability of Reinforcement Problems with Arbitrary Dependence.- Probabilistic Generalization of Simple Grammars and Its Application to Reinforcement Learning.- Unsupervised Slow Subspace-Learning from Stationary Processes.- Learning-Related Complexity of Linear Ranking Functions.