13 search results - page 1 / 3 » Beyond Logarithmic Bounds in Online Learning |
JMLR
2012
12 years 24 days ago
2012
We prove logarithmic regret bounds that depend on the loss L∗ T of the competitor rather than on the number T of time steps. In the general online convex optimization setting, o...
ALT
2008
Springer
14 years 7 months ago
2008
Springer
Abstract. We consider an upper confidence bound algorithm for Markov decision processes (MDPs) with deterministic transitions. For this algorithm we derive upper bounds on the onl...
COLT
2006
Springer
14 years 2 months ago
2006
Springer
In an online convex optimization problem a decision-maker makes a sequence of decisions, i.e., chooses a sequence of points in Euclidean space, from a fixed feasible set. After ea...
CORR
2011
Springer
13 years 5 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...
ICML
2007
IEEE
14 years 11 months ago
2007
IEEE
A number of updates for density matrices have been developed recently that are motivated by relative entropy minimization problems. The updates involve a softmin calculation based...