We consider the Multi-armed bandit problem under the PAC (“probably approximately correct”) model. It was shown by Even-Dar et al. [5] that given n arms, it suffices to play th...
We examine the so-called rigorous support vector machine (RSVM) approach proposed by Vapnik (1998). The formulation of RSVM is derived by explicitly implementing the structural ris...
This paper extends the game-theoretic notion of internal regret to the case of on-line potfolio selection problems. New sequential investment strategies are designed to minimize th...
We study on-line play of repeated matrix games in which the observations of past actions of the other player and the obtained reward are partial and stochastic. We define the Part...
Abstract. In this paper we initiate an exploration of relationships between “preference elicitation”, a learning-style problem that arises in combinatorial auctions, and the pr...
Avrim Blum, Jeffrey C. Jackson, Tuomas Sandholm, M...