Algorithmic Learning Theory: 19th International Conference, Alt 2008, Budapest, Hungary, October 13-16, 2008, Proceedings

by Freund, Yoav; Gyorfi, Laszlo; Turan, Gyorgy; Zeugmann, Thomas

• ISBN13: 9783540879862
• ISBN10: 3540879862
• Format: Paperback
• Copyright: 2008-12-04
• Publisher: Springer-Verlag New York Inc

Summary

This book constitutes the refereed proceedings of the 19th International Conference on Algorithmic Learning Theory, ALT 2008, held in Budapest, Hungary, in October 2008, co-located with the 11th International Conference on Discovery Science, DS 2008.The 31 revised full papers presented together with the abstracts of 5 invited talks were carefully reviewed and selected from 46 submissions. The papers are dedicated to the theoretical foundations of machine learning; they address topics such as statistical learning; probability and stochastic processes; boosting and experts; active and query learning; and inductive inference.

Table of Contents

Invited Papers
On Iterative Algorithms with an Information Geometry Background	p. 1
Visual Analytics: Combining Automated Discovery with Interactive Visualizations	p. 2
Some Mathematics behind Graph Property Testing	p. 3
Finding Total and Partial Orders from Data for Seriation	p. 4
Computational Models of Neural Representations in the Human Brain (Extended Abstract)	p. 5
Regular Contributions
Statistical Learning
Generalization Bounds for Some Ordinal Regression Algorithms	p. 7
Approximation of the Optimal ROC Curve and a Tree-Based Ranking Algorithm	p. 22
Sample Selection Bias Correction Theory	p. 38
Exploiting Cluster-Structure to Predict the Labeling of a Graph	p. 54
A Uniform Lower Error Bound for Half-Space Learning	p. 70
Generalization Bounds for K-Dimensional Coding Schemes in Hilbert Spaces	p. 79
Learning and Generalization with the Information Bottleneck	p. 92
Probability and Stochastic Processes
Growth Optimal Investment with Transaction Costs	p. 108
Online Regret Bounds for Markov Decision Processes with Deterministic Transitions	p. 123
On-Line Probability, Complexity and Randomness	p. 138
Prequential Randomness	p. 154
Some Sufficient Conditions on an Arbitrary Class of Stochastic Processes for the Existence of a Predictor	p. 169
Nonparametric Independence Tests: Space Partitioning and Kernel Approaches	p. 183
Boosting and Experts
Supermartingales in Prediction with Expert Advice	p. 199
Aggregating Algorithm for a Space of Analytic Functions	p. 214
Smooth Boosting for Margin-Based Ranking	p. 227
Learning with Continuous Experts Using Drifting Games	p. 240
Entropy Regularized LPBoost	p. 256
Active Learning and Queries
Optimally Learning Social Networks with Activations and Suppressions	p. 272
Active Learning in Multi-armed Bandits	p. 287
Query Learning and Certificates in Lattices	p. 303
Clustering with Interactive Feedback	p. 316
Active Learning of Group-Structured Environments	p. 329
Finding the Rare Cube	p. 344
Inductive Inference
Iterative Learning of Simple External Contextual Languages	p. 359
Topological Properties of Concept Spaces	p. 374
Dynamically Delayed Postdictive Completeness and Consistency in Learning	p. 389
Dynamic Modeling in Inductive Inference	p. 404
Optimal Language Learning	p. 419
Numberings Optimal for Learning	p. 434
Learning with Temporary Memory	p. 449
Erratum
Erratum: Constructing Multiclass Learners from Binary Learners: A Simple Black-Box Analysis of the Generalization Errors	p. 464
Author Index	p. 467
Table of Contents provided by Ingram. All Rights Reserved.