Management Science and Information Systems' Seminar（2019-07）

Topic: Stochastic Gradient Estimation: Efficient Learning Technique Under Uncertainty

Speaker: Yijie Peng，the Department of Industrial Engineering and Management, Peking University

Time: Tuesday, April 9, 2019, 14:00--15:45 p.m

Place: Room 216 , Guanghua Building 2

Abstract:

Stochastic gradient estimation plays a central role in sensitivity analysis and gradient-based optimization. Particularly, it serves as the most important tool for training artificial neural networks in deep learning. We propose a generalized likelihood ratio (GLR) estimator in a framework that can handle discontinuous sample performances with structural parameters. This work extends classic unbiased stochastic derivative estimators to a setting where they did not previously apply. The GLR estimator can deal with many applications in a single umbrella and preserves the single-run efficiency. Applications of GLR on financial engineering, risk management, and artificial intelligence will be presented.

Introduction:

Dr. Yijie Peng is currently an assistant professor of the Department of Industrial Engineering and Management at Peking University (PKU). He received his Ph.D. from the Department of Management Science at Fudan University and his B.S. degree from the School of Mathematics at Wuhan University. Before joining PKU, he worked as an assistant professor at George Mason University, and postdoctoral scholar at Fudan University and R.H. Smith School of Business at University of Maryland at College Park. Many of his publications appear in high-quality journals including Operations Research, IEEE Transactions on Automatic Control, INFORMS Journal on Computing, Journal of Discrete Event Dynamic System, and Quantitative Finance. His research interests include stochastic modeling and analysis, simulation optimization, machine learning, data analytics, and healthcare.

Your participation is warmly welcomed!