1106 search results - page 168 / 222 » On regularization algorithms in learning theory |
136
click to vote
ICML
2006
IEEE
16 years 5 months ago
2006
IEEE
Boosting methods are known not to usually overfit training data even as the size of the generated classifiers becomes large. Schapire et al. attempted to explain this phenomenon i...
135
click to vote
ATAL
2010
Springer
15 years 5 months ago
2010
Springer
In this paper we study, for the first time explicitly, the implications of endowing an interested party (i.e. a teacher) with the ability to modify the underlying dynamics of the ...
137
click to vote
JAIR
2006
15 years 4 months ago
2006
The most basic assumption used in statistical learning theory is that training data and test data are drawn from the same underlying distribution. Unfortunately, in many applicati...
136
click to vote
ALT
2008
Springer
16 years 1 months ago
2008
Springer
Abstract. Classical probability theory considers probability distributions that assign probabilities to all events (at least in the finite case). However, there are natural situat...
140
click to vote
COLT
1999
Springer
15 years 8 months ago
1999
Springer
We present a unified framework for reasoning about worst-case regret bounds for learning algorithms. This framework is based on the theory of duality of convex functions. It brin...