University of Connecticut

Events Calendar


Control And Optimization Seminar
Solving High-Dimensional Control Problems With Deep Learning
Jiequn Han (Princeton University)

Monday, April 26, 2021
2:00pm – 3:00pm

Other
online

Webex Meeting link: https://uconn-cmr.webex.com/uconn-cmr/j.php?MTID=m95ba63b09b9269ee906df8c8c8c8675f

Meeting number: 120 069 1816 Password: UConn

Abstract: The development of deep learning has provided us new powerful tools to solve high-dimensional problems. This talk will start with a control-viewpoint of deep learning, discussing the connection between optimizing neural networks and solving optimal control problems. Inspired by such a connection, we will present two lines of research that leverage deep learning to solve high-dimensional control problems: (1) solving stochastic control problems, with possible delay effect; (2) solving parabolic PDEs based on backward stochastic differential equations (BSDE). The numerical results suggest that the proposed algorithms achieve satisfactory accuracy and, at the same time, can handle rather high-dimensional problems. This opens up new possibilities in economics, finance, and operational research, by considering more realistic and informative high-dimensional states.

Speaker's short bio: Dr. Han is an Instructor of Mathematics at the Department of Mathematics and the Program in Applied and Computational Mathematics (PACM), Princeton University. He obtained his Ph.D. from Princeton in 2018 and B.S. from Peking University if 2013. His search draws inspiration from various disciplines of science and is devoted to solving high-dimensional problems arising from scientific computing. Please visit his website for more information: https://web.math.princeton.edu/~jiequnh/

Contact:

Bin Zou, bin.zou@uconn.edu

Control and Optimization (primary), UConn Master Calendar

Control Panel