We present a modification of the algorithm of Dani et al. [8] for the online linear optimization problem in the bandit setting, which with high probability has regret at most O ( ...
Peter L. Bartlett, Varsha Dani, Thomas P. Hayes, S...
We present an algorithm running in time O(n log n) which decides if a wreathclosed permutation class Av(B) given by its finite basis B contains a finite number of simple permutati...
Recent work has looked at extending clustering algorithms with instance level must-link (ML) and cannot-link (CL) background information. Our work introduces δ and ǫ cluster lev...
Exploratory ad-hoc queries could return too many answers ? a phenomenon commonly referred to as "information overload". In this paper, we propose to automatically catego...
This paper examines the problem of finding an optimal policy for a Partially Observable Markov Decision Process (POMDP) when the model is not known or is only poorly specified. W...