83 search results - page 3 / 17 » Online Learning: Beyond Regret |
ICML
2009
IEEE
14 years 8 months ago
2009
IEEE
We study online learning in an oblivious changing environment. The standard measure of regret bounds the difference between the cost of the online learner and the best decision in...
COLT
2010
Springer
13 years 5 months ago
2010
Springer
Bandit convex optimization is a special case of online convex optimization with partial information. In this setting, a player attempts to minimize a sequence of adversarially gen...
CVPR
2010
IEEE
14 years 3 months ago
2010
IEEE
Multiple instance (MI) learning is a recent learning paradigm that is more flexible than standard supervised learning algorithms in the handling of label ambiguity. It has been u...
CORR
2011
Springer
13 years 2 months ago
2011
Springer
In this paper we study the online learning problem involving rested and restless multiarmed bandits with multiple plays. The system consists of a single player/user and a set of K...
ALT
2010
Springer
13 years 9 months ago
2010
Springer
: In many prediction problems, including those that arise in computer security and computational finance, the process generating the data is best modeled as an adversary with whom ...