Learning Theory

19th Annual Conference on Learning Theory, COLT 2006, Pittsburgh, PA, USA, June 22-25, 2006. Proceedings

Editors:

ISBN: 978-3-540-35294-5 (Print) 978-3-540-35296-9 (Online)

Table of contents (48 chapters)

previous Page of 3
  1. Front Matter

    Pages -

  2. Invited Presentations

    1. No Access

      Book Chapter

      Pages 1-1

      Random Multivariate Search Trees

    2. No Access

      Book Chapter

      Pages 2-3

      On Learning and Logic

    3. No Access

      Book Chapter

      Pages 4-4

      Predictions as Statements and Decisions

  3. Clustering, Un-, and Semisupervised Learning

    1. No Access

      Book Chapter

      Pages 5-19

      A Sober Look at Clustering Stability

    2. No Access

      Book Chapter

      Pages 20-34

      PAC Learning Axis-Aligned Mixtures of Gaussians with No Separation Assumption

    3. No Access

      Book Chapter

      Pages 35-49

      Stable Transductive Learning

    4. No Access

      Book Chapter

      Pages 50-64

      Uniform Convergence of Adaptive Graph-Based Regularization

  4. Statistical Learning Theory

    1. No Access

      Book Chapter

      Pages 65-78

      The Rademacher Complexity of Linear Transformation Classes

    2. No Access

      Book Chapter

      Pages 79-93

      Function Classes That Approximate the Bayes Risk

    3. No Access

      Book Chapter

      Pages 94-108

      Functional Classification with Margin Conditions

    4. No Access

      Book Chapter

      Pages 109-122

      Significance and Recovery of Block Structures in Binary Matrices with Noise

  5. Regularized Learning and Kernel Methods

    1. No Access

      Book Chapter

      Pages 123-138

      Maximum Entropy Distribution Estimation with Generalized Regularization

    2. No Access

      Book Chapter

      Pages 139-153

      Unifying Divergence Minimization and Statistical Inference Via Convex Duality

    3. No Access

      Book Chapter

      Pages 154-168

      Mercer’s Theorem, Feature Maps, and Smoothing

    4. No Access

      Book Chapter

      Pages 169-183

      Learning Bounds for Support Vector Machines with Learned Kernels

  6. Query Learning and Teaching

    1. No Access

      Book Chapter

      Pages 184-198

      On Optimal Learning Algorithms for Multiplicity Automata

    2. No Access

      Book Chapter

      Pages 199-213

      Exact Learning Composed Classes with a Small Number of Mistakes

    3. No Access

      Book Chapter

      Pages 214-228

      DNF Are Teachable in the Average Case

    4. No Access

      Book Chapter

      Pages 229-243

      Teaching Randomized Learners

  7. Inductive Inference

    1. No Access

      Book Chapter

      Pages 244-258

      Memory-Limited U-Shaped Learning

previous Page of 3