CISE Seminar: November 15, 2019 – Henry Lam

Simulation-based prediction, for instance in discrete-event analysis and machine learning, often incurs errors from both Monte Carlo computation and calibration noise from data. These errors, if overlooked, can result in incorrect inference and underestimation of risks that degrade decision-making. We present several methods to efficiently quantify these errors, by injecting subsampling, distributionally robust optimization, and random perturbation respectively into simulation runs. We explain the statistical mechanisms of these approaches and why they help resolve each of the discussed challenges faced by existing methods. This is joint work with Huajie Qian (Columbia).

Henry Lam is an Associate Professor in the Department of Industrial Engineering and Operations Research at Columbia University. He received his Ph.D. degree in statistics from Harvard University in 2011, and was on the faculty of Boston University and the University of Michigan before joining Columbia in 2017. Henry’s research interests include Monte Carlo simulation, risk and extremal analysis, and optimization under uncertainty. He serves on the editorial boards of Operations Research, INFORMS Journal on Computing, and Stochastic Models.