Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming


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… (More)
DOI: 10.1137/120880811


5 Figures and Tables


Citations per Year

162 Citations

Semantic Scholar estimates that this publication has 162 citations based on the available data.

See our FAQ for additional information.