The U-Lagrangian of a prox-regular function
Shuai Liu, Andrew Eberhard, Yousong Luo

TL;DR
This paper extends the concept of U-Lagrangian and UV-decomposition from convex to nonconvex prox-regular functions, enabling smoother analysis of nonsmooth functions in subspaces.
Contribution
It generalizes the U-Lagrangian and UV-decomposition framework to nonconvex prox-regular functions, broadening their applicability.
Findings
Defines U-Lagrangian for prox-regular functions.
Establishes properties of the generalized UV-decomposition.
Provides theoretical insights into nonsmooth nonconvex optimization.
Abstract
When restricted to a subspace, a nonsmooth function can be differentiable. It is known that for a nonsmooth convex function f and a point x, the Euclidean space can be decomposed into two subspaces: U, over which a special Lagrangian can be defined and has nice smooth properties and V, the orthogonal complement subspace of U. In this paper we generalize the definition of UV-decomposition and U-Lagrangian to the context of nonconvex functions, specifically that of a prox-regular function.
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
TopicsOptimization and Variational Analysis · Advanced Optimization Algorithms Research · Iterative Methods for Nonlinear Equations
