Sciweavers

Share
COLT
2006
Springer
10 years 10 days ago
Can Entropic Regularization Be Replaced by Squared Euclidean Distance Plus Additional Linear Constraints
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...
Manfred K. Warmuth
COLT
2006
Springer
10 years 10 days ago
The Shortest Path Problem Under Partial Monitoring
András György, Tamás Linder, Gy...
COLT
2006
Springer
10 years 2 months ago
Online Variance Minimization
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...
Manfred K. Warmuth, Dima Kuzmin
COLT
2006
Springer
10 years 2 months ago
Online Learning Meets Optimization in the Dual
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...
Shai Shalev-Shwartz, Yoram Singer
COLT
2006
Springer
10 years 2 months ago
Ranking with a P-Norm Push
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...
Cynthia Rudin
COLT
2006
Springer
10 years 2 months ago
Mercer's Theorem, Feature Maps, and Smoothing
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...
Ha Quang Minh, Partha Niyogi, Yuan Yao
books