Editors’ Introduction -- Editors’ Introduction -- Invited Papers -- Towards General Algorithms for Grammatical Inference -- The Blessing and the Curse of the Multiplicative Updates -- Discovery of Abstract Concepts by a Robot -- Contrast Pattern Mining and Its Application for Building Robust Classifiers -- Optimal Online Prediction in Adversarial Environments -- Regular Contributions -- An Algorithm for Iterative Selection of Blocks of Features -- Bayesian Active Learning Using Arbitrary Binary Valued Queries -- Approximation Stability and Boosting -- A Spectral Approach for Probabilistic Grammatical Inference on Trees -- PageRank Optimization in Polynomial Time by Stochastic Shortest Path Reformulation -- Inferring Social Networks from Outbreaks -- Distribution-Dependent PAC-Bayes Priors -- PAC Learnability of a Concept Class under Non-atomic Measures: A Problem by Vidyasagar -- A PAC-Bayes Bound for Tailored Density Estimation -- Compressed Learning with Regular Concept -- A Lower Bound for Learning Distributions Generated by Probabilistic Automata -- Lower Bounds on Learning Random Structures with Statistical Queries -- Recursive Teaching Dimension, Learning Complexity, and Maximum Classes -- Toward a Classification of Finite Partial-Monitoring Games -- Switching Investments -- Prediction with Expert Advice under Discounted Loss -- A Regularization Approach to Metrical Task Systems -- Solutions to Open Questions for Non-U-Shaped Learning with Memory Limitations -- Learning without Coding -- Learning Figures with the Hausdorff Metric by Fractals -- Inductive Inference of Languages from Samplings -- Optimality Issues of Universal Greedy Agents with Static Priors -- Consistency of Feature Markov Processes -- Algorithms for Adversarial Bandit Problems with Multiple Plays -- Online Multiple Kernel Learning: Algorithms and Mistake Bounds -- An Identity for Kernel Ridge Regression.

This book constitutes the refereed proceedings of the 21th International Conference on Algorithmic Learning Theory, ALT 2010, held in Canberra, Australia, in October 2010, co-located with the 13th International Conference on Discovery Science, DS 2010. The 26 revised full papers presented together with the abstracts of 5 invited talks were carefully reviewed and selected from 44 submissions. The papers are divided into topical sections of papers on statistical learning; grammatical inference and graph learning; probably approximately correct learning; query learning and algorithmic teaching; on-line learning; inductive inference; reinforcement learning; and on-line learning and kernel methods.