COLT 2002

27 papers

A Consistent Strategy for Boosting Algorithms Gábor Lugosi, Nicolas Vayatis

A Second-Order Perceptron Algorithm Nicolò Cesa-Bianchi, Alex Conconi, Claudio Gentile

Agnostic Learning Nonconvex Function Classes Shahar Mendelson, Robert C. Williamson

Bounds for the Minimum Disagreement Problem with Applications to Learning Theory Nader H. Bshouty, Lynn Burroughs

Entropy, Combinatorial Dimensions and Random Averages Shahar Mendelson, Roman Vershynin

Exploring Learnability Between Exact and PAC Nader H. Bshouty, Jeffrey C. Jackson, Christino Tamon

Geometric Parameters of Kernel Machines Shahar Mendelson

Inferring Deterministic Linear Languages Colin de la Higuera, José Oncina

Learning the Internet Christos H. Papadimitriou

Learning Tree Languages from Text Henning Fernau

Localized Rademacher Complexities Peter L. Bartlett, Olivier Bousquet, Shahar Mendelson

Maximizing the Margin with Boosting Gunnar Rätsch, Manfred K. Warmuth

Merging Uniform Inductive Learners Sandra Zilles

Mixability and the Existence of Weak Complexities Yuri Kalnishkan, Michael V. Vyugin

New Lower Bounds for Statistical Query Learning Ke Yang

On the Proper Learning of Axis Parallel Concepts Nader H. Bshouty, Lynn Burroughs

PAC Bounds for Multi-Armed Bandit and Markov Decision Processes Eyal Even-Dar, Shie Mannor, Yishay Mansour

Path Kernels and Multiplicative Updates Eiji Takimoto, Manfred K. Warmuth

Performance Guarantees for Hierarchical Clustering Sanjoy Dasgupta

Polynomial Time Inductive Inference of Ordered Tree Patterns with Internal Structured Variables from Positive Data Yusuke Suzuki, Ryuta Akanuma, Takayoshi Shoudai, Tetsuhiro Miyahara, Tomoyuki Uchida

Prediction and Dimension Lance Fortnow, Jack H. Lutz

Predictive Complexity and Information Michael V. Vyugin, Vladimir V. V'yugin

Self-Optimizing and Pareto-Optimal Policies in General Environments Based on Bayes-Mixtures Marcus Hutter

Some Local Measures of Complexity of Convex Hulls and Generalization Bounds Olivier Bousquet, Vladimir Koltchinskii, Dmitriy Panchenko

The Consistency of Greedy Algorithms for Classification Shie Mannor, Ron Meir, Tong Zhang

The Speed Prior: A New Simplicity Measure Yielding Near-Optimal Computable Predictions Jürgen Schmidhuber

Tracking Linear-Threshold Concepts with Winnow Chris Mesterharm