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

This document was uploaded by one of our users. The uploader already confirmed that they had the permission to publish it. If you are author/publisher or own the copyright of this documents, please report to us by using this DMCA report form.

Simply click on the Download Book button.

Yes, Book downloads on Ebookily are 100% Free.

Sometimes the book is free on Amazon As well, so go ahead and hit "Search on Amazon"

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.

Author(s): Sanjoy Dasgupta (auth.), Ricard Gavaldà , Gábor Lugosi, Thomas Zeugmann, Sandra Zilles (eds.)
Series: Lecture Notes in Computer Science 5809 : Lecture Notes in Artificial Intelligence
Edition: 1
Publisher: Springer Berlin Heidelberg
Year: 2009

Language: English
Pages: 409


Content:
Front Matter....Pages -
The Two Faces of Active Learning....Pages 1-1
Inference and Learning in Planning....Pages 2-2
Mining Heterogeneous Information Networks by Exploring the Power of Links....Pages 3-3
Learning and Domain Adaptation....Pages 4-6
Learning on the Web....Pages 7-7
Prediction with Expert Evaluators’ Advice....Pages 8-22
Pure Exploration in Multi-armed Bandits Problems....Pages 23-37
The Follow Perturbed Leader Algorithm Protected from Unbounded One-Step Losses....Pages 38-52
Computable Bayesian Compression for Uniformly Discretizable Statistical Models....Pages 53-67
Calibration and Internal No-Regret with Random Signals....Pages 68-82
St. Petersburg Portfolio Games....Pages 83-96
Reconstructing Weighted Graphs with Minimal Query Complexity....Pages 97-109
Learning Unknown Graphs....Pages 110-125
Completing Networks Using Observed Data....Pages 126-140
Average-Case Active Learning with Costs....Pages 141-155
Canonical Horn Representations and Query Learning....Pages 156-170
Learning Finite Automata Using Label Queries....Pages 171-185
Characterizing Statistical Query Learning: Simplified Notions and Proofs....Pages 186-200
An Algebraic Perspective on Boolean Function Learning....Pages 201-215
Adaptive Estimation of the Optimal ROC Curve and a Bipartite Ranking Algorithm....Pages 216-231
Complexity versus Agreement for Many Views....Pages 232-246
Error-Correcting Tournaments....Pages 247-262
Difficulties in Forcing Fairness of Polynomial Time Inductive Inference....Pages 263-277
Learning Mildly Context-Sensitive Languages with Multidimensional Substitutability from Positive Data....Pages 278-292
Uncountable Automatic Classes and Learning....Pages 293-307
Iterative Learning from Texts and Counterexamples Using Additional Information....Pages 308-322
Incremental Learning with Ordinal Bounded Example Memory....Pages 323-337
Learning from Streams....Pages 338-352
Smart PAC-Learners....Pages 353-367
Approximation Algorithms for Tensor Clustering....Pages 368-383
Agnostic Clustering....Pages 384-398
Back Matter....Pages -