Sciweavers

COLT
1997
Springer
13 years 11 months ago
Algorithmic Stability and Sanity-Check Bounds for Leave-one-Out Cross-Validation
: In this paper we prove sanity-check bounds for the error of the leave-one-out cross-validation estimate of the generalization error: that is, bounds showing that the worst-case e...
Michael J. Kearns, Dana Ron
COLT
1997
Springer
13 years 11 months ago
General Convergence Results for Linear Discriminant Updates
The problem of learning linear discriminant concepts can be solved by various mistake-driven update procedures, including the Winnow family of algorithms and the well-known Percep...
Adam J. Grove, Nick Littlestone, Dale Schuurmans
COLT
1997
Springer
13 years 11 months ago
Inferring Answers to Queries
William I. Gasarch, Andrew C. Y. Lee
COLT
1997
Springer
13 years 11 months ago
On-line Learning and the Metrical Task System Problem
We relate two problems that have been explored in two distinct communities. The first is the problem of combining expert advice, studied extensively in the computational learning...
Avrim Blum, Carl Burch
COLT
1997
Springer
13 years 11 months ago
Estimation of Time-Varying Parameters in Statistical Models: An Optimization Approach
Abstract. We propose a convex optimization approach to solving the nonparametric regression estimation problem when the underlying regression function is Lipschitz continuous. This...
Dimitris Bertsimas, David Gamarnik, John N. Tsitsi...
ALT
1997
Springer
13 years 11 months ago
Learning DFA from Simple Examples
Efficient learning of DFA is a challenging research problem in grammatical inference. It is known that both exact and approximate (in the PAC sense) identifiability of DFA is har...
Rajesh Parekh, Vasant Honavar
ALT
1997
Springer
13 years 11 months ago
Synthesizing Noise-Tolerant Language Learners
An index for an r.e. class of languages (by definition) generates a sequence of grammars defining the class. An index for an indexed family of languages (by definition) generat...
John Case, Sanjay Jain, Arun Sharma
ICML
1997
IEEE
13 years 11 months ago
A Comparative Study on Feature Selection in Text Categorization
This paper is a comparative study of feature selection methods in statistical learning of text categorization. The focus is on aggressive dimensionality reduction. Five methods we...
Yiming Yang, Jan O. Pedersen
SEAL
1998
Springer
13 years 11 months ago
Genetic Programming with Active Data Selection
Genetic programming evolves Lisp-like programs rather than fixed size linear strings. This representational power combined with generality makes genetic programming an interesting ...
Byoung-Tak Zhang, Dong-Yeon Cho