Remarks on the $\Gamma $-regularization of Non-convex and Non-semi-continuous Functions on Topological Vector Spaces
J.-B. Bru, W. de Siqueira Pedra

TL;DR
This paper introduces a method using $ ext{Gamma}$-regularization to analyze minimization problems of non-convex, non-semi-continuous functions on topological vector spaces, extending known theorems to broader contexts.
Contribution
It presents a novel approach to study non-convex functions via convex regularization and generalizes the Lanford III-Robinson theorem beyond separable Banach spaces.
Findings
Establishes $ ext{Gamma}$-regularization as a key tool for non-convex minimization.
Generalizes the Lanford III-Robinson theorem to all locally convex real spaces.
Provides a new framework for understanding subdifferentials of non-convex functions.
Abstract
We show that the minimization problem of any non-convex and non-lower semi-continuous function on a compact convex subset of a locally convex real topological vector space can be studied via an associated convex and lower semi-continuous function . This observation uses the notion of -regularization as a key ingredient. As an application we obtain, on any locally convex real space, a generalization of the Lanford III-Robinson theorem which has only been proven for separable real Banach spaces. The latter is a characterization of subdifferentials of convex continuous functions.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Banach Space Theory · Optimization and Variational Analysis · Approximation Theory and Sequence Spaces
