Guided by the goal of obtaining an optimization algorithm that is both fast and yields good generalization, we study the descent direction maximizing the decrease in generalizatio...
Nicolas Le Roux, Pierre-Antoine Manzagol, Yoshua B...
This paper presents an algorithm for recovering the globally optimal 2D human figure detection using a loopy graph model. This is computationally challenging because the time comp...
Recently, we have introduced a novel approach to dynamic programming and reinforcement learning that is based on maintaining explicit representations of stationary distributions i...
Tao Wang, Daniel J. Lizotte, Michael H. Bowling, D...
We present and analyze an algorithm to solve numerically BSDEs based on Picard's iterations and on a sequential control variate technique. Its convergence is geometric. Moreov...
Research in efficient methods for solving infinite-horizon MDPs has so far concentrated primarily on discounted MDPs and the more general stochastic shortest path problems (SSPs...
Andrey Kolobov, Mausam, Daniel S. Weld, Hector Gef...