234 search results - page 2 / 47 » Rademacher Margin Complexity |
COLT
2007
Springer
13 years 11 months ago
2007
Springer
We present data-dependent error bounds for transductive learning based on transductive Rademacher complexity. For specific algorithms we provide bounds on their Rademacher complex...
NIPS
2007
13 years 6 months ago
2007
This paper1 explores the use of a Maximal Average Margin (MAM) optimality principle for the design of learning algorithms. It is shown that the application of this risk minimizati...
ICML
2004
IEEE
14 years 6 months ago
2004
IEEE
Boosting is a popular approach for building accurate classifiers. Despite the initial popular belief, boosting algorithms do exhibit overfitting and are sensitive to label noise. ...
ALT
2004
Springer
14 years 2 months ago
2004
Springer
Rademacher and Gaussian complexities are successfully used in learning theory for measuring the capacity of the class of functions to be learned. One of the most important propert...
NECO
2010
13 years 3 months ago
2010
In this paper we develop a novel generalization bound for learning the kernel problem. First, we show that the generalization analysis of the kernel learning problem reduces to in...