138 search results - page 1 / 28 » Entropy Numbers of Linear Function Classes |
COLT
2000
Springer
13 years 9 months ago
2000
Springer
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...
FSE
2008
Springer
13 years 7 months ago
2008
Springer
Abstract. A corrector is used to reduce or eliminate statistical weakness of a physical random number generator. A description of linear corrector generalizing post-processing desc...
JMLR
2002
13 years 5 months ago
2002
Recently, sample complexity bounds have been derived for problems involving linear functions such as neural networks and support vector machines. In many of these theoretical stud...
ICPR
2004
IEEE
14 years 6 months ago
2004
IEEE
We discuss the relationship between the discriminative training of Gaussian models and the maximum entropy framework for log-linear models. Observing that linear transforms leave ...
TSP
2010
13 years 1 days ago
2010
A novel (differential) entropy estimator is introduced where the maximum entropy bound is used to approximate the entropy given the observations, and is computed using a numerical ...