Computational Learning Theory: 4th European Conference, Eurocolt '99, Nordkirchen, Germany, March 29-31, 1999 Proceedings

by Fischer, Paul; Simon, Hans Ulrich

• ISBN13: 9783540657019
• ISBN10: 3540657010
• Format: Paperback
• Copyright: 1999-04-01
• Publisher: Springer Verlag

Summary

This book constitutes the refereed proceedings of the 4th European Conference on Computational Learning Theory, EuroCOLT'99, held in Nordkirchen, Germany in March 1999. The 21 revised full papers presented were selected from a total of 35 submissions; also included are two invited contributions. The book is divided in topical sections on learning from queries and counterexamples, reinforcement learning, online learning and export advice, teaching and learning, inductive inference, and statistical theory of learning and pattern recognition.

Table of Contents

Invited Lectures
Theoretical Views of Boosting	1	(10)
Robert E. Schapire
Open Theoretical Questions in Reinforcement Learning	11	(7)
Richard S. Sutton
Learning from Random Examples
A Geometric Approach to Leveraging Weak Learners	18	(16)
Nigel Duffy
David Helmbold
Query by Committee, Linear Separation and Random Walks	34	(16)
Ran Bachrach
Shai Fine
Eli Shamir
Hardness Results for Neural Network Approximation Problems	50	(13)
Peter Bartlett
Shai Ben-David
Learning from Queries and Counterexamples
Learnability of Quantified Formulas	63	(16)
Victor Dalmau
Peter Jeavons
Learning Multiplicity Automata from Smallest Counterexamples	79	(12)
Jurgen Forster
Exact Learning when Irrelevant Variables Abound	91	(10)
David Guijarro
Victor Lavin
Vijay Raghavan
An Application of Codes to Attribute-Efficient Learning	101	(10)
Thomas Hofmeister
Learning Range Restricted Horn Expressions	111	(15)
Roni Khardon
Reinforcement Learning
On the Asymptotic Behavior of a Constant Stepsize Temporal-Difference Learning Algorithm	126	(12)
Vladislav Tadic
On-line Learning and Expert Advice
Direct and Indirect Algorithms for On-line Learning of Disjunctions	138	(15)
D.P. Helmbold
S. Panizza
M. K. Warmuth
Averaging Expert Predictions	153	(15)
Jyrki Kivinen
Manfred K. Warmuth
Teaching and Learning
On Teaching and Learning Intersection-Closed Concept Classes	168	(15)
Christian Kuhlmann
Inductive Inference
Avoiding Coding Tricks by Hyperrobust Learning	183	(15)
Matthias Ott
Frank Stephan
Mind Change Complexity of Learning Logic Programs	198	(16)
Sanjay Jain
Arun Sharma
Statistical Theory of Learning and Pattern Recognition
Regularized Principal Manifolds	214	(16)
Alex J. Smola
Robert C. Williamson
Sebastian Mika
Bernhard Scholkopf
Distribution-Dependent Vapnik-Chervonenkis Bounds	230	(11)
Nicolas Vayatis
Robert Azencott
Lower Bounds on the Rate of Convergence of Nonparametric Pattern Recognition	241	(12)
Andras Antos
On Error Estimation for the Partitioning Classification Rule	253	(10)
Marta Horvath
Margin Distribution Bounds on Generalization	263	(11)
John Shawe-Taylor
Nello Cristianini
Generalization Performance of Classifiers in Terms of Observed Covering Numbers	274	(11)
John Shawe-Taylor
Robert C. Williamson
Entropy Numbers, Operators and Support Vector Kernels	285	(16)
Robert C. Williamson
Alex J. Smola
Bernhard Scholkopf
Author Index	301