Searcharxiv⌕ Search

arXiv · 2611.17164

From Metric to Strong Metric Regularity: A Second Subderivative Criterion for Definable Prox-regular Subdifferentials

Abstract

We investigate when metric regularity of a subdifferential mapping rules out multiple local inverse branches and therefore upgrades to strong metric regularity. Let $h:\mathbb{R}^n\to(-\infty,\infty]$ be proper, lower semicontinuous, definable, prox-regular, and subdifferentially continuous at $(\bar x,\bar v)\in\operatorname{gph}(\partial h)$. We characterize this ``upgrade'' through the second subderivative $q = \mathrm{d}^2h(\bar x|\bar v)$ of $h$. If $\partial h$ is metrically regular, then it is strongly metrically regular if and only if the set of negative curvature directions of $q$ on the unit sphere of $\operatorname{span}(\operatorname{dom}(q))$ has Euler characteristic $0$ or $2$. We also prove a simpler and directly verifiable sufficient condition: nonnegativity of $q$ on the lineality space $\operatorname{dom}(q)\cap(-\operatorname{dom}(q))$ forces a quadratic lower bound for $q$ on its entire domain and hence yields strong metric regularity. In particular, if $\bar x$ is a local minimizer and $\bar v=0$, the second subderivative is nonnegative on its domain $\operatorname{dom}(q)$, which proves a conjecture of Drusvyatskiy, Mordukhovich, and Nghia in the definable setting. The derived principle strengthens this conjecture by replacing local minimality with a weaker second-order condition on the lineality space.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Wenqing Ouyang, Andre Milzarek. 2026-11-12. From Metric to Strong Metric Regularity: A Second Subderivative Criterion for Definable Prox-regular Subdifferentials. https://searcharxiv.com/abs/2611.17164

Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.

KEEP EXPLORING

Related papers

First-order methods for stochastic and finite-sum convex optimization with deterministic constraints

In this paper, we study a class of stochastic and finite-sum convex optimization problems with deterministic constraints. Existing methods typically aim to find an $ε$-$expected\ feasible\ stochastic\ optimal$ solution, in which both the expected constraint violation and the expected optimality gap are within a prescribed tolerance $ε$. However, in many practical applications, constraints must be nearly satisfied with certainty, rendering such solutions potentially unsuitable due to the risk of substantial violations. To address this issue, we propose stochastic first-order methods for finding an $ε$-$surely\ feasible\ stochastic\ optimal$ ($ε$-SFSO) solution, where the constraint violation is deterministically bounded by $ε$ and the expected optimality gap is at most $ε$. Our methods apply an accelerated stochastic gradient (ASG) scheme or a modified variance-reduced ASG scheme $only\ once$ to a sequence of quadratic penalty subproblems with appropriately chosen penalty parameters. We establish first-order oracle complexity bounds for the proposed methods in computing an $ε$-SFSO solution. Preliminary numerical results are presented to illustrate the performance of the proposed methods.

math.OC↗

Attention's forward pass and Frank-Wolfe

We study the hardmax limit of self-attention dynamics for token embeddings obtained in the zero-temperature ($β\to+\infty$) regime, and relate it to the finite-$β$ setting. In this limit, the update rule can be viewed as a Frank-Wolfe step for a quadratic objective over the convex hull of the current token embeddings. When the key-query matrix is negative semidefinite, the method linearly contracts all tokens to a single cluster at the origin. When it is positive semidefinite, extending the hardmax rule to the entire convex hull induces a Voronoi diagram: vertices are stationary, interior points remain in their initial cells, and each token moves along a straight line toward its cell's vertex, yielding (super-)exponential convergence. As a byproduct, we also establish well-posedness of the associated ODE limit in this regime. Returning to the finite-$β$ regime, we model self-attention dynamics as a Markov chain and prove dynamic metastability: with high probability, interior tokens reach near-vertex configurations in a constant number of steps and remain within a small neighborhood for times that grow exponentially in the inverse temperature $β$, before ultimately collapsing to the origin. Thus, the hardmax dynamics accurately approximate the finite-$β$ process over exponentially long time horizons.

math.OC↗

Finite de Finetti for convex bodies and Polynomial Optimization

We study polynomial optimization over convex bodies with separately affine objectives and local affine equality and inequality constraints. We construct a convergent hierarchy of conic relaxations with explicit finite-level error bounds of order $n^{-1/2}$ at level $n$, complemented by a constructive rounding scheme that produces feasible points. The relaxation bounds and rounded objective values bracket the optimum at the same rate. The analytic ingredient is a finite de Finetti representation theorem for arbitrary proper cones: bipartite marginals of symmetric extensions in maximal tensor products are $O(n^{-1/2})$-close, in base norm, to points of the minimal tensor product. Its proof combines a uniform, monogamy-type bound on a variational mutual information based on Frenkel's relative entropy with classical conditioning and informationally complete measurements. We apply the framework to the assemblage relaxation of two-player non-local games in general probabilistic theories. For polytopic state spaces, the hierarchy consists of linear programs, and experiments on the Clauser--Horne--Shimony--Holt (CHSH) game provide a numerical proof of concept for the outer approximations and feasible rounding procedure.

math.OC↗