Learning Theory and Kernel Machines [electronic resource] : 16th Annual Conference on Learning Theory and 7th Kernel Workshop, COLT/Kernel 2003, Washington, DC, USA, August 24-27, 2003. Proceedings /

Target Area: Computational Game Theory -- Tutorial: Learning Topics in Game-Theoretic Decision Making -- A General Class of No-Regret Learning Algorithms and Game-Theoretic Equilibria -- Preference Elicitation and Query Learning -- Efficient Algorithms for Online Decision Problems -- Positive Definite Rational Kernels -- Bhattacharyya and Expected Likelihood Kernels -- Maximal Margin Classification for Metric Spaces -- Maximum Margin Algorithms with Boolean Kernels -- Knowledge-Based Nonlinear Kernel Classifiers -- Fast Kernels for Inexact String Matching -- On Graph Kernels: Hardness Results and Efficient Alternatives -- Kernels and Regularization on Graphs -- Data-Dependent Bounds for Multi-category Classification Based on Convex Losses -- Poster Session 1 -- Comparing Clusterings by the Variation of Information -- Multiplicative Updates for Large Margin Classifiers -- Simplified PAC-Bayesian Margin Bounds -- Sparse Kernel Partial Least Squares Regression -- Sparse Probability Regression by Label Partitioning -- Learning with Rigorous Support Vector Machines -- Robust Regression by Boosting the Median -- Boosting with Diverse Base Classifiers -- Reducing Kernel Matrix Diagonal Dominance Using Semi-definite Programming -- Optimal Rates of Aggregation -- Distance-Based Classification with Lipschitz Functions -- Random Subclass Bounds -- PAC-MDL Bounds -- Universal Well-Calibrated Algorithm for On-Line Classification -- Learning Probabilistic Linear-Threshold Classifiers via Selective Sampling -- Learning Algorithms for Enclosing Points in Bregmanian Spheres -- Internal Regret in On-Line Portfolio Selection -- Lower Bounds on the Sample Complexity of Exploration in the Multi-armed Bandit Problem -- Smooth ?-Insensitive Regression by Loss Symmetrization -- On Finding Large Conjunctive Clusters -- Learning Arithmetic Circuits via Partial Derivatives -- Poster Session 2 -- Using a Linear Fit to Determine Monotonicity Directions -- Generalization Bounds for Voting Classifiers Based on Sparsity and Clustering -- Sequence Prediction Based on Monotone Complexity -- How Many Strings Are Easy to Predict? -- Polynomial Certificates for Propositional Classes -- On-Line Learning with Imperfect Monitoring -- Exploiting Task Relatedness for Multiple Task Learning -- Approximate Equivalence of Markov Decision Processes -- An Information Theoretic Tradeoff between Complexity and Accuracy -- Learning Random Log-Depth Decision Trees under the Uniform Distribution -- Projective DNF Formulae and Their Revision -- Learning with Equivalence Constraints and the Relation to Multiclass Learning -- Target Area: Natural Language Processing -- Tutorial: Machine Learning Methods in Natural Language Processing -- Learning from Uncertain Data -- Learning and Parsing Stochastic Unification-Based Grammars -- Generality’s Price -- On Learning to Coordinate -- Learning All Subfunctions of a Function -- When Is Small Beautiful? -- Learning a Function of r Relevant Variables -- Subspace Detection: A Robust Statistics Formulation -- How Fast Is k-Means? -- Universal Coding of Zipf Distributions -- An Open Problem Regarding the Convergence of Universal A Priori Probability -- Entropy Bounds for Restricted Convex Hulls -- Compressing to VC Dimension Many Points.