Time: Friday, May 22, 2026, 10:30-11:30 a.m.

Venue: Room 524, Siyuan Building, Guoshun Campus

Topic: Black-Box Quantile Optimization Using Finite Difference-Based Gradient Approximation

Speaker: Professor Jiaqiao Hu, State University of New York at Stony Brook

Host: Professor Jianqiang Hu

Abstract: We propose two new iterative multi-timescale stochastic gradient descent algorithms for solving quantile optimization problems under a general black-box setting. The first algorithm uses an appropriately modified finite-difference-based gradient estimator that requires 2d+1 samples of the black-box function per iteration, where d denotes the number of decision variables. The second algorithm employs a simultaneous-perturbation-based gradient estimator that uses only three samples per iteration regardless of problem dimension. We establish the almost sure convergence of both algorithms and derive their convergence rates. Numerical experiments are also presented to illustrate and compare the performance of the proposed algorithms with alternative methods.

Bio:

Jiaqiao Hu is a Professor in the Department of Applied Mathematics and Statistics at the State University of New York at Stony Brook. He received his B.E. degree in Automation from Shanghai Jiao Tong University, his M.S. degree in Applied Mathematics from the University of Maryland, Baltimore County, and his Ph.D. degree in Electrical Engineering from the University of Maryland, College Park. His research interests include Markov decision processes, simulation optimization, and stochastic modeling and analysis. He has served on the editorial boards of Operations Research, IISE Transactions, and Journal of Systems & Management.