Bolte, JérômeIdRef, Pauwels, EdouardIdRef and Silveti Falls, AntonioIdRef (2024) Differentiating nonsmooth solutions to parametric monotone inclusion problems. SIAM Journal on Optimization, Vol. 34 (N° 1/2024).

This is the latest version of this item.

Full text not available from this repository.
Identification Number : 10.1137/22M1541630

Abstract

We 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, with formulas for computing its generalized gradient. A direct consequence of our result is that these solutions happen to be differentiable almost everywhere. Our approach is fully compatible with automatic differentiation and comes with the following assumptions which are easy to check (roughly speaking): semialgebraicity and strong monotonicity. We illustrate the scope of our results by considering the following three fundamental composite problem settings: strongly convex problems, dual solutions to convex minimization problems, and primal-dual solutions to min-max problems.

Item Type: Article
Language: English
Date: 2024
Refereed: Yes
Place of Publication: Philadelphia
Subjects: B- ECONOMIE ET FINANCE
Divisions: TSE-R (Toulouse)
Site: UT1
Date Deposited: 12 Feb 2025 08:43
Last Modified: 24 Apr 2025 07:39
OAI Identifier: oai:tse-fr.eu:130339
URI: https://publications.ut-capitole.fr/id/eprint/50435

Available Versions of this Item

View Item