+612 9045 4394
Learning Theory and Kernel Machines : 16th Annual Conference on Computational Learning Theory and 7th Kernel Workshop, Colt/Kernel 2003, Washington, DC, Usa, August 24-27, 2003, Proceedings - Bernhard Scholkopf

Learning Theory and Kernel Machines

16th Annual Conference on Computational Learning Theory and 7th Kernel Workshop, Colt/Kernel 2003, Washington, DC, Usa, August 24-27, 2003, Proceedings

By: Bernhard Scholkopf (Editor), Manfred K Warmuth (Editor)

Paperback Published: 11th August 2003
ISBN: 9783540407201
Number Of Pages: 754

Share This Book:


or 4 easy payments of $51.04 with Learn more
Ships in 5 to 9 business days

This volume contains papers presented at the joint 16th Annual Conference on Learning Theory (COLT) and the 7th Annual Workshop on Kernel Machines, heldinWashington, DC, USA, duringAugust24-27,2003.COLT, whichrecently merged with EuroCOLT, has traditionally been a meeting place for learning theorists. We hope that COLT will bene't from the collocation with the annual workshoponkernelmachines, formerlyheldasaNIPSpostconferenceworkshop. The technical program contained 47 papers selected from 92 submissions. All 47paperswerepresentedasposters;22ofthepaperswereadditionallypresented astalks.Therewerealsotwotargetareaswithinvitedcontributions.Incompu- tional game theory, atutorialentitled"LearningTopicsinGame-TheoreticDe- sionMaking"wasgivenbyMichaelLittman, andaninvitedpaperon"AGeneral Class of No-Regret Learning Algorithms and Game-Theoretic Equilibria" was contributed by Amy Greenwald. In natural language processing, a tutorial on "Machine Learning Methods in Natural Language Processing" was presented by Michael Collins, followed by two invited talks, "Learning from Uncertain Data" by Mehryar Mohri and "Learning and Parsing Stochastic Uni?cation- Based Grammars" by Mark Johnson. In addition to the accepted papers and invited presentations, we solicited short open problems that were reviewed and included in the proceedings. We hope that reviewed open problems might become a new tradition for COLT. Our goal was to select simple signature problems whose solutions are likely to inspire further research. For some of the problems the authors o?ered monetary rewards. Yoav Freund acted as the open problem area chair. The open problems were presented as posters at the conference.

Target Area: Computational Game Theory
Tutorial: Learning Topics in Game-Theoretic Decision Makingp. 1
Invited Talk
A General Class of No-Regret Learning Algorithms and Game-Theoretic Equilibriap. 2
Contributed Talks
Preference Elicitation and Query Learningp. 13
Efficient Algorithms for Online Decision Problemsp. 26
Kernel Machines
Positive Definite Rational Kernelsp. 41
Bhattacharyya and Expected Likelihood Kernelsp. 57
Maximal Margin Classification for Metric Spacesp. 72
Maximum Margin Algorithms with Boolean Kernelsp. 87
Knowledge-Based Nonlinear Kernel Classifiersp. 102
Fast Kernels for Inexact String Matchingp. 114
On Graph Kernels: Hardness Results and Efficient Alternativesp. 129
Kernels and Regularization on Graphsp. 144
Data-Dependent Bounds for Multi-category Classification Based on Convex Lossesp. 159
Poster Session 1
Comparing Clusterings by the Variation of Informationp. 173
Multiplicative Updates for Large Margin Classifiersp. 188
Simplified PAC-Bayesian Margin Boundsp. 203
Sparse Kernel Partial Least Squares Regressionp. 216
Sparse Probability Regression by Label Partitioningp. 231
Learning with Rigorous Support Vector Machinesp. 243
Robust Regression by Boosting the Medianp. 258
Boosting with Diverse Base Classifiersp. 273
Reducing Kernel Matrix Diagonal Dominance Using Semi-definite Programmingp. 288
Statistical Learning Theory
Optimal Rates of Aggregationp. 303
Distance-Based Classification with Lipschitz Functionsp. 314
Random Subclass Boundsp. 329
PAC-MDL Boundsp. 344
Online Learning
Universal Well-Calibrated Algorithm for On-Line Classificationp. 358
Learning Probabilistic Linear-Threshold Classifiers via Selective Samplingp. 373
Learning Algorithms for Enclosing Points in Bregmanian Spheresp. 388
Internal Regret in On-Line Portfolio Selectionp. 403
Other Approaches
Lower Bounds on the Sample Complexity of Exploration in the Multi-armed Bandit Problemp. 418
Smooth e-Insensitive Regression by Loss Symmetrizationp. 433
On Finding Large Conjunctive Clustersp. 448
Learning Arithmetic Circuits via Partial Derivativesp. 463
Poster Session 2
Using a Linear Fit to Determine Monotonicity Directionsp. 477
Generalization Bounds for Voting Classifiers Based on Sparsity and Clusteringp. 492
Sequence Prediction Based on Monotone Complexityp. 506
How Many Strings Are Easy to Predict?p. 522
Polynomial Certificates for Propositional Classesp. 537
On-Line Learning with Imperfect Monitoringp. 552
Exploiting Task Relatedness for Multiple Task Learningp. 567
Approximate Equivalence of Markov Decision Processesp. 581
An Information Theoretic Tradeoff between Complexity and Accuracyp. 595
Learning Random Log-Depth Decision Trees under the Uniform Distributionp. 610
Projective DNF Formulae and Their Revisionp. 625
Learning with Equivalence Constraints and the Relation to Multiclass Learningp. 640
Target Area: Natural Language Processing
Tutorial: Machine Learning Methods in Natural Language Processingp. 655
Invited Talks
Learning from Uncertain Datap. 656
Learning and Parsing Stochastic Unification-Based Grammarsp. 671
Inductive Inference Learning
Generality's Price: Inescapable Deficiencies in Machine-Learned Programsp. 684
On Learning to Coordinate: Random Bits Help, Insightful Normal Forms, and Competency Isomorphismsp. 699
Learning All Subfunctions of a Functionp. 714
Open Problems
When Is Small Beautiful?p. 729
Learning a Function of r Relevant Variablesp. 731
Subspace Detection: A Robust Statistics Formulationp. 734
How Fast Is k Means?p. 735
Universal Coding of Zipf Distributionsp. 736
An Open Problem Regarding the Convergence of Universal A Priori Probabilityp. 738
Entropy Bounds for Restricted Convex Hullsp. 741
Compressing to VC Dimension Many Pointsp. 743
Author Indexp. 745
Table of Contents provided by Publisher. All Rights Reserved.

ISBN: 9783540407201
ISBN-10: 3540407200
Series: Lecture Notes in Computer Science / Lecture Notes in Artific
Audience: General
Format: Paperback
Language: English
Number Of Pages: 754
Published: 11th August 2003
Publisher: Springer-Verlag Berlin and Heidelberg Gmbh & Co. Kg
Country of Publication: DE
Dimensions (cm): 23.39 x 15.6  x 3.89
Weight (kg): 1.06