73 search results - page 2 / 15 » Stochastic Linear Optimization under Bandit Feedback |
CORR
2010
Springer
13 years 18 days ago
2010
Springer
In the classic multi-armed bandits problem, the goal is to have a policy for dynamically operating arms that each yield stochastic rewards with unknown means. The key metric of int...
FSTTCS
2010
Springer
13 years 3 months ago
2010
Springer
Given a zero-sum infinite game we examine the question if players have optimal memoryless deterministic strategies. It turns out that under some general conditions the problem for...
INFOCOM
2007
IEEE
13 years 12 months ago
2007
IEEE
—The implementation of distributed network utility maximization (NUM) algorithms hinges heavily on information feedback through message passing among network elements. In practic...
MP
2008
13 years 5 months ago
2008
In this paper we discuss computational complexity and risk averse approaches to two and multistage stochastic programming problems. We argue that two stage (say linear) stochastic ...
INFOCOM
2008
IEEE
14 years 1 days ago
2008
IEEE
Abstract—Motivated by the increasing usage of wireless broadcast networks for multicast real-time applications like video, this paper considers a canonical real-time multicast sc...