SDS Statistics Seminar Series

Topic

Recent Advances in Bayesian Optimization for The Physical and Engineering Sciences

Speaker

Simon MAK, Assistant Professor, Statistical Science, Duke University

Host

Sheng JIANG, Assistant Professor, School of Data Science, CUHK-Shenzhen

Date

23 January (Thursday), 2025

Time

4:00 PM- 5:00 PM, Beijing Time

Format

Hybrid

Venue

Room 401, Dao Yuan Building

Zoom Link

https://cuhk-edu-cn.zoom.us/j/94204079326?pwd=Xw6KsOLQObyyOfBaND8y8IkJrgAJta.1

Meeting ID: 942 0407 9326, Password: 800588

Language

English

Abstract

With advances in scientific computing, computer simulations are increasingly used for investigating complex physical phenomena. For many such applications, scientific decision-making involves optimizing the simulator output, which can be costly given the expensive nature of simulation runs. While Bayesian optimization (BO) offers a promising solution, there are key challenges that limit the use of existing BO methods in the physical sciences. The first is the presence of noise parameters, which are controllable in the simulator but uncontrollable in reality. For this, we propose a new Targeted Variance Reduction (TVR) method, for optimizing a black-box simulator given random uncertainty on noise parameters. Using a carefully specified Gaussian process surrogate, the TVR admits a closed-form acquisition function via normalizing flows, thus allowing for efficient sequential sampling. We explore the effectiveness of TVR in numerical experiments and an application for automobile brake design under operational uncertainties. The second challenge is the need for diverse optimization solutions, which provide users with a basket of "good" solutions for decision-making. For this, we propose a new Diverse Expected Improvement (DEI) method, which extends the popular Expected Improvement method to encourage diversity between near-optimal solutions. The DEI similarly yields a closed-form acquisition function, which reveals a novel exploration-exploitation-diversity trade-off for diverse black-box optimization. We explore the effectiveness of the DEI in two applications, the first on rover trajectory optimization and the second for optimizing diverse microbiome communities for biotic heterogeneity.

Biography

Simon Mak is an Assistant Professor of Statistical Science at Duke University. His research involves integrating domain scientific knowledge for cost-efficient statistical learning and decision-making with expensive scientific experiments. His ongoing research stems from interdisciplinary collaborations in high-energy physics, aerospace engineering and public policy, and is supported by the National Science Foundation and the Department of Energy. He is currently the Program Chair-Elect of the ASA Section on Physical and Engineering Sciences, the Deputy Spokesperson of JETSCAPE (a multi-institutional collaboration on high-energy physics), and an Associate Editor for Technometrics and Data Science in Science.