22 search results - page 5 / 5 » High-Probability Regret Bounds for Bandit Online Linear Opti... |
CORR
2010
Springer
13 years 3 months ago
2010
Springer
Online prediction methods are typically presented as serial algorithms running on a single processor. However, in the age of web-scale prediction problems, it is increasingly comm...
ICML
2007
IEEE
14 years 6 months ago
2007
IEEE
In this paper, we present an information-theoretic approach to learning a Mahalanobis distance function. We formulate the problem as that of minimizing the differential relative e...