The PRIMO Group is proud to announce the next talk of the 2023-2024 season of the “PRIMO Talks” series.
The seminar will be held on Thursday February 22, 2024 at 5pm (CET).
Speaker: Tony Silveti-Falls (CentraleSupélec – Université Paris-Saclay)
Title: Differentiating Nonsmooth Solutions to Parametric Monotone Inclusion Problems
Abstract:
Understanding the differentiability and regularity of the solution to a monotone inclusion problem is an important question with consequences for convex optimization, deep learning with implicit layers, and beyond. Past attempts at answering this question have been made either under very restrictive assumptions that ensure the solution is continuously differentiable or using mathematical tools that are incompatible with automatic differentiation. In this talk, we discuss how to leverage path differentiability and a recent result on nonsmooth implicit differentiation calculus to give sufficient conditions ensuring that the solution to a monotone inclusion problem will be path differentiable and provide formulas for computing its generalized gradient. Our approach is fully compatible with automatic differentiation and comes with assumptions which are easy to check, roughly speaking: semialgebraicity and strong monotonicity. We illustrate the scope of our results by considering three fundamental composite problem settings: strongly convex problems, dual solutions to convex minimization problems and primal-dual solutions to min-max problems.
The Zoom link to the event will be shared through the PRIMO mailing list and other related mailing lists.
PRIMO Research group 