Skip to content

ISE Graduate Seminar

Fusing Deep Learning and Optimization

Abstract: The fusion of deep learning and optimization has the potential to deliver outcomes for engineering applications that the two technologies cannot achieve independently. This talk illustrates this potential with the concept of optimization proxy, a differentiable program that can produce, in milliseconds, feasible (or near-feasible) and near-optimal solutions to classes of optimization problems. The talk reviews some of the foundations underlying optimization proxies, including end-to-end learning, compact optimization learning, dual learning, and self-supervised learning. The benefits of optimization proxies are demonstrated on applications in power systems and supply

Bio: Pascal Van Hentenryck is the director of the NSF AI Institute for Advances in Optimization (AI4OPT) and the A. Russell Chandler III Chair and Professor at the Georgia Institute of Technology. Several of his optimization systems have been in commercial use for more than 20 years. His current research focuses on AI for Engineering, fusing machine learning and optimization for applications in energy systems, supply chains and manufacturing, and mobility. Van Hentenryck is a
fellow of AAAI and INFORMS, and the recipients of numerous research and teaching awards. He was also a Ulam fellow at the Los Alamos National Laboratories.

Dial-In Information

Friday, October 27, 2023 at 1:50pm to 2:40pm

John D. Tickle Engineering Building, 500
851 Neyland Dr, Knoxville, TN 37996

Event Type

Lectures & Presentations




Current Students, Faculty & Staff




Industrial and Systems Engineering
Contact Name

Jim Ostrowski

Contact Email

Google Calendar iCal Outlook

Recent Activity