COLT
2006
Springer
13 years 7 months ago
2006
Springer
There are two main families of on-line algorithms depending on whether a relative entropy or a squared Euclidean distance is used as a regularizer. The difference between the two f...
COLT
2006
Springer
13 years 7 months ago
2006
Springer
COLT
2006
Springer
13 years 8 months ago
2006
Springer
We design algorithms for two online variance minimization problems. Specifically, in every trial t our algorithms get a covariance matrix Ct and try to select a parameter vector wt...
COLT
2006
Springer
13 years 8 months ago
2006
Springer
COLT
2006
Springer
13 years 8 months ago
2006
Springer
COLT
2006
Springer
13 years 8 months ago
2006
Springer
COLT
2006
Springer
13 years 8 months ago
2006
Springer
We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a sub-family of universa...
COLT
2006
Springer
13 years 8 months ago
2006
Springer
We are interested in supervised ranking with the following twist: our goal is to design algorithms that perform especially well near the top of the ranked list, and are only requir...
COLT
2006
Springer
13 years 8 months ago
2006
Springer
COLT
2006
Springer
13 years 8 months ago
2006
Springer
We study Mercer's theorem and feature maps for several positive definite kernels that are widely used in practice. The smoothing properties of these kernels will also be explo...