Classically, an approach to the multiagent policy learning supposed that the agents, via interactions and/or by using preliminary knowledge about the reward functions of all playe...
With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...
Power-performance optimization is a relatively new problem area particularly in the context of server clusters. Poweraware request distribution is a method of scheduling service r...
Nonsmoothness pervades optimization, but the way it typically arises is highly structured. Nonsmooth behavior of an objective function is usually associated, locally, with an activ...
Abstract. This paper introduces an outlier rejection and signal reconstruction method for high angular resolution diffusion weighted imaging. The approach is based on the threshold...
Carl-Fredrik Westin, Marc Niethammer, Martha Eliza...