457 citations · 696 across the 72 of their papers we have counts for
6 papers · 2 filters
Orthounimodal Distributionally Robust Optimization: Representation, Computation and Multivariate Extreme Event Applications
Henry Lam, Zhenyuan Liu, Xinyu Zhang
This paper studies a basic notion of distributional shape known as orthounimodality (OU) and its use in shape-constrained distributionally robust optimization (DRO). As a key motiv…
Higher-Order Expansion and Bartlett Correctability of Distributionally Robust Optimization
Shengyi He, Henry Lam
Distributionally robust optimization (DRO) is a worst-case framework for stochastic optimization under uncertainty that has drawn fast-growing studies in recent years. When the und…
Generalization Bounds with Minimal Dependency on Hypothesis Class via Distributionally Robust Optimization
Yibo Zeng, Henry Lam
Established approaches to obtain generalization bounds in data-driven optimization and machine learning mostly build on solutions from empirical risk minimization (ERM), which depe…
On the Impossibility of Statistically Improving Empirical Optimization: A Second-Order Stochastic Dominance Perspective
Henry Lam
When the underlying probability distribution in a stochastic optimization is observed only through data, various data-driven formulations have been studied to obtain approximate op…
Distributionally Constrained Black-Box Stochastic Gradient Estimation and Optimization
Henry Lam, Junhui Zhang
We consider stochastic gradient estimation using only black-box function evaluations, where the function argument lies within a probability simplex. This problem is motivated from…
General Feasibility Bounds for Sample Average Approximation via Vapnik-Chervonenkis Dimension
Henry Lam, Fengpei Li
We investigate the feasibility of sample average approximation (SAA) for general stochastic optimization problems, including two-stage stochastic programming without the relatively…