FacebookTwitterGoogle PlusRSS News Feed

Seminar

Seminars
Assistant Professor of Industrial and Systems Engineering
University of Florida
Stochastic First-and Zeroth-Order Methods for Nonconvex Stochastic Programming
Friday, March 28, 2014 - 1:30pm to 3:00pm
151 
Posner Hall
Abstract:

In this paper, we introduce a new stochastic approximation (SA) type algorithm, namely the randomized stochastic gradient (RSG) method, for solving an important class of nonlinear (possibly nonconvex) stochastic programming (SP) problems. We establish the complexity of this method for computing an approximate stationary point of a nonlinear programming problem. We also show that this method possesses a nearly optimal rate of convergence if the problem is convex. We discuss a variant of the algorithm which consists of applying a post-optimization phase to evaluate a short list of solutions generated by several independent runs of the RSG method, and show that such modification allows to improve significantly the large-deviation properties of the algorithm. These methods are then specialized for solving a class of simulation-based optimization problems in which only stochastic zeroth-order information is available.

For More Information, Please Contact:

aramdas [atsymbol] cs ~replace-with-a-dot~ cmu ~replace-with-a-dot~ edu