3/6/25 | 4:15pm | E51-376
Pascal Van Hentenryck
A. Russell Chandler III Chair and Professor
Georgia Institute of Technology
Abstract: This talk considers the concept of trustworthy optimization learning, a methodology to design optimization proxies that learn the input/output mapping of parametric optimization problems. These optimization proxies are trustworthy by design: they compute feasible solutions to the underlying optimization problems, provide quality guarantees on the returned solutions, and scale to large instances. Optimization proxies are differentiable programs that combine traditional deep learning technology with repair or completion layers to produce feasible solutions. The talk discusses how optimization proxies can be trained end-to-end in a self-supervised way. It presents methodologies to provide performance guarantees and to scale optimization proxies to large-scale optimization problems. The potential of optimization proxies is highlighted through applications in power systems and, in particular, real-time risk assessment and security-constrained optimal power flow, and in supply chains and logistics.
Bio: Pascal Van Hentenryck is the director of Tech AI (the AI Hub at Georgia Tech), the director of the NSF AI Institute for Advances in Optimization (AI4OPT), and the A. Russell Chandler III Chair and Professor at Georgia Tech. He was a professor at Computer Science at Brown University for over 20 years and led the optimization research group at the National ICT Research, Australia. His current research focuses on Responsible AI for Engineering with applications in energy systems, supply chains, manufacturing, health care, and mobility. Van Hentenryck is a pioneer of constraint programming, and he designed and implemented several innovative optimization systems that have been in commercial use for over 20 years, including the CHIP and OPL systems.