Algorithmic Learning Theory: 20th International Conference, ALT 2009, Porto, Portugal, October 3-5, 2009, Proceedings

This book constitutes the refereed proceedings of the 20th International Conference on Algorithmic Learning Theory, ALT 2009, held in Porto, Portugal, in October 2009, co-located with the 12th International Conference on Discovery Science, DS 2009. The 26 revised full papers presented together with the abstracts of 5 invited talks were carefully reviewed and selected from 60 submissions. The papers are divided into topical sections of papers on online learning, learning graphs, active learning and query learning, statistical learning, inductive inference, and semisupervised and unsupervised learning. The volume also contains abstracts of the invited talks: Sanjoy Dasgupta, The Two Faces of Active Learning; Hector Geffner, Inference and Learning in Planning; Jiawei Han, Mining Heterogeneous; Information Networks By Exploring the Power of Links, Yishay Mansour, Learning and Domain Adaptation; Fernando C.N. Pereira, Learning on the Web.

Table of Contents:
Invited Papers.- The Two Faces of Active Learning.- Inference and Learning in Planning.- Mining Heterogeneous Information Networks by Exploring the Power of Links.- Learning and Domain Adaptation.- Learning on the Web.- Regular Contributions.- Prediction with Expert Evaluators’ Advice.- Pure Exploration in Multi-armed Bandits Problems.- The Follow Perturbed Leader Algorithm Protected from Unbounded One-Step Losses.- Computable Bayesian Compression for Uniformly Discretizable Statistical Models.- Calibration and Internal No-Regret with Random Signals.- St. Petersburg Portfolio Games.- Reconstructing Weighted Graphs with Minimal Query Complexity.- Learning Unknown Graphs.- Completing Networks Using Observed Data.- Average-Case Active Learning with Costs.- Canonical Horn Representations and Query Learning.- Learning Finite Automata Using Label Queries.- Characterizing Statistical Query Learning: Simplified Notions and Proofs.- An Algebraic Perspective on Boolean Function Learning.- Adaptive Estimation of the Optimal ROC Curve and a Bipartite Ranking Algorithm.- Complexity versus Agreement for Many Views.- Error-Correcting Tournaments.- Difficulties in Forcing Fairness of Polynomial Time Inductive Inference.- Learning Mildly Context-Sensitive Languages with Multidimensional Substitutability from Positive Data.- Uncountable Automatic Classes and Learning.- Iterative Learning from Texts and Counterexamples Using Additional Information.- Incremental Learning with Ordinal Bounded Example Memory.- Learning from Streams.- Smart PAC-Learners.- Approximation Algorithms for Tensor Clustering.- Agnostic Clustering.