PHOENIX, AZ: Dr. Guanghui (George) Lan, Assistant Professor of Industrial and Systems Engineering, and his Ph.D. student Saeed Ghadimi were named winners of the 2012 Institute for Operations Research and the Management Sciences (INFORMS) JFIG (Junior Faculty Interest Group) Paper Competition at the annual JFIG luncheon on Monday, October 15. Their paper, “Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming,” took first place out of 50 entries. Six finalists presented the work on Sunday morning at the annual INFORMS conference. Dr. Jeff Linderoth of the University of Wisconsin presented Dr. Lan the award at the luncheon.
The paper introduces novel randomized stochastic gradient methods for solving an important class of nonlinear, and possibly nonconvex, stochastic programming problems. New complexity bounds and strong large-deviation properties are presented for these algorithms, along with promising numerical results. Specialized stochastic zeroth-order algorithms are also developed for solving a class of simulation-based optimization problems. This work seems to be the first effort in developing nonconvex stochastic gradient methods in the literature.
The JFIG Forum of INFORMS was created in 2001 to promote the career development of tenure-track faculty in operations research. According to the INFORMS website, the paper competition is meant to encourage and promote research among junior faculty in the field.