Local Nonconvexity Indices for \(C^{1,1}\) Functions via Generalized Hessians
Marina Palaisti

TL;DR
This paper introduces a local nonconvexity index for C^{1,1} functions using generalized Hessians, extending previous smooth indices to nonsmooth settings with desirable invariance and continuity properties.
Contribution
It develops a spectral interval-valued local nonconvexity index for C^{1,1} functions based on generalized Hessians, generalizing smooth indices to nonsmooth functions.
Findings
The index reduces to the classical smooth index for C^2 functions.
It vanishes for convex C^{1,1} functions.
The index is invariant under orthogonal transformations.
Abstract
Davydov, Moldavskaya, and Zitikis introduced local indices for quantifying the lack of convexity of a \(C^2\) function by measuring the nuclear-norm distance of its Hessian from the cone of positive semidefinite matrices. This paper develops a local analogue for functions of class \(C^{1,1}\). At a point \(x\), the classical Hessian is replaced by the Clarke-type generalized Hessian set \(\Hess(h;x)\), defined as the closed convex hull of limiting Hessians at nearby twice differentiability points. Evaluating the same spectral functional over \(\Hess(h;x)\) gives an interval-valued local nonconvexity index whose lower and upper endpoints represent, respectively, the least and greatest visible second-order nonconvexity at \(x\). The construction reduces to the original smooth index when \(h\in C^2\), vanishes for convex \(C^{1,1}\) functions, is invariant under orthogonal changes of…
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.
