Sciweavers

COLT
2001
Springer
15 years 10 months ago
Agnostic Boosting
We prove strong noise-tolerance properties of a potential-based boosting algorithm, similar to MadaBoost (Domingo and Watanabe, 2000) and SmoothBoost (Servedio, 2003). Our analysi...
Shai Ben-David, Philip M. Long, Yishay Mansour
COLT
2001
Springer
15 years 10 months ago
Ultraconservative Online Algorithms for Multiclass Problems
In this paper we study a paradigm to generalize online classification algorithms for binary classification problems to multiclass problems. The particular hypotheses we investig...
Koby Crammer, Yoram Singer
COLT
2001
Springer
15 years 10 months ago
Robust Learning - Rich and Poor
A class C of recursive functions is called robustly learnable in the sense I (where I is any success criterion of learning) if not only C itself but even all transformed classes ...
John Case, Sanjay Jain, Frank Stephan, Rolf Wiehag...
COLT
2001
Springer
15 years 10 months ago
Data-Dependent Margin-Based Generalization Bounds for Classification
Balázs Kégl, Tamás Linder, G&...
COLT
2001
Springer
15 years 10 months ago
Limitations of Learning via Embeddings in Euclidean Half-Spaces
The notion of embedding a class of dichotomies in a class of linear half spaces is central to the support vector machines paradigm. We examine the question of determining the mini...
Shai Ben-David, Nadav Eiron, Hans-Ulrich Simon
Machine Learning
Top of PageReset Settings