Sciweavers

Share
warning: Creating default object from empty value in /var/www/modules/taxonomy/taxonomy.module on line 1416.
COLT
2000
Springer
10 years 4 months ago
The Role of Critical Sets in Vapnik-Chervonenkis Theory
In the present paper, we present the theoretical basis, as well as an empirical validation, of a protocol designed to obtain effective VC dimension estimations in the case of a si...
Nicolas Vayatis
COLT
2000
Springer
10 years 4 months ago
Leveraging for Regression
In this paper we examine master regression algorithms that leverage base regressors by iteratively calling them on modified samples. The most successful leveraging algorithm for c...
Nigel Duffy, David P. Helmbold
COLT
2000
Springer
10 years 4 months ago
MadaBoost: A Modification of AdaBoost
Carlos Domingo, Osamu Watanabe
COLT
2000
Springer
10 years 5 months ago
Entropy Numbers of Linear Function Classes
This paper collects together a miscellany of results originally motivated by the analysis of the generalization performance of the “maximum-margin” algorithm due to Vapnik and...
Robert C. Williamson, Alex J. Smola, Bernhard Sch&...
COLT
2000
Springer
10 years 5 months ago
Average-Case Complexity of Learning Polynomials
The present paper deals with the averagecase complexity of various algorithms for learning univariate polynomials. For this purpose an appropriate framework is introduced. Based o...
Frank Stephan, Thomas Zeugmann
COLT
2000
Springer
10 years 5 months ago
PAC Analogues of Perceptron and Winnow via Boosting the Margin
We describe a novel family of PAC model algorithms for learning linear threshold functions. The new algorithms work by boosting a simple weak learner and exhibit complexity bounds...
Rocco A. Servedio
COLT
2000
Springer
10 years 5 months ago
Barrier Boosting
Boosting algorithms like AdaBoost and Arc-GV are iterative strategies to minimize a constrained objective function, equivalent to Barrier algorithms. Based on this new understandi...
Gunnar Rätsch, Manfred K. Warmuth, Sebastian ...
COLT
2000
Springer
10 years 5 months ago
On the Convergence Rate of Good-Turing Estimators
Good-Turing adjustments of word frequencies are an important tool in natural language modeling. In particular, for any sample of words, there is a set of words not occuring in tha...
David A. McAllester, Robert E. Schapire
COLT
2000
Springer
10 years 5 months ago
Boosting Using Branching Programs
Yishay Mansour, David A. McAllester
COLT
2000
Springer
10 years 5 months ago
Computable Shell Decomposition Bounds
Haussler, Kearns, Seung and Tishby introduced the notion of a shell decomposition of the union bound as a means of understanding certain empirical phenomena in learning curves suc...
John Langford, David A. McAllester
books