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...
The application of statistical methods to natural language processing has been remarkably successful over the past two decades. But, to deal with recent problems arising in this ļ¬...
We propose a new formulation of the clustering problem that diļ¬ers from previous work in several aspects. First, the goal is to explicitly output a collection of simple and meani...
We consider the Multi-armed bandit problem under the PAC (āprobably approximately correctā) model. It was shown by Even-Dar et al. [5] that given n arms, it suļ¬ces to play 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 deļ¬ne the Part...
Recent work has introduced Boolean kernels with which one can learn linear threshold functions over a feature space containing all conjunctions of length up to k (for any 1 ā¤ k ...