70 search results - page 8 / 14 » Using Generalization Error Bounds to Train the Set Covering ... |
ICML
2005
IEEE
14 years 8 months ago
2005
IEEE
We consider online learning where the target concept can change over time. Previous work on expert prediction algorithms has bounded the worst-case performance on any subsequence ...
JMLR
2002
13 years 7 months ago
2002
A central problem in learning is selection of an appropriate model. This is typically done by estimating the unknown generalization errors of a set of models to be selected from a...
ICML
2003
IEEE
14 years 8 months ago
2003
IEEE
Recent theoretical results have shown that improved bounds on generalization error of classifiers can be obtained by explicitly taking the observed margin distribution of the trai...
JMLR
2010
13 years 2 months ago
2010
In this paper, we propose a general framework for sparse semi-supervised learning, which concerns using a small portion of unlabeled data and a few labeled data to represent targe...
COLT
1995
Springer
13 years 11 months ago
1995
Springer
The Noise Sensitivity Signature (NSS), originally introduced by Grossman and Lapedes (1993), was proposed as an alternative to cross validation for selecting network complexity. I...