97 search results - page 11 / 20 » Logarithmic Regret Algorithms for Online Convex Optimization |
174
click to vote
ICML
2003
IEEE
16 years 6 months ago
2003
IEEE
Convex programming involves a convex set F Rn and a convex cost function c : F R. The goal of convex programming is to find a point in F which minimizes c. In online convex prog...
173
Voted
COLT
2010
Springer
15 years 3 months ago
2010
Springer
We consider the problem of planning in a stochastic and discounted environment with a limited numerical budget. More precisely, we investigate strategies exploring the set of poss...
173
click to vote
COLT
2010
Springer
15 years 3 months ago
2010
Springer
We consider the problem of finding the best arm in a stochastic multi-armed bandit game. The regret of a forecaster is here defined by the gap between the mean reward of the optim...
174
click to vote
LION
2010
Springer
15 years 9 months ago
2010
Springer
Abstract. Algorithm selection is typically based on models of algorithm performance learned during a separate offline training sequence, which can be prohibitively expensive. In r...
146
Voted
COLT
2004
Springer
15 years 11 months ago
2004
Springer
We give an algorithm for the bandit version of a very general online optimization problem considered by Kalai and Vempala [1], for the case of an adaptive adversary. In this proble...