Salvato in:
Dettagli Bibliografici
Autori principali: Li, Qin, Li, Sixu, Tadmor, Eitan, Trélat, Emmanuel
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2605.24485
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918519875043328
author Li, Qin
Li, Sixu
Tadmor, Eitan
Trélat, Emmanuel
author_facet Li, Qin
Li, Sixu
Tadmor, Eitan
Trélat, Emmanuel
contents We study a finite-horizon stochastic control criterion for non-convex optimization in which Brownian exploration is balanced against a quadratic control cost. Rather than emphasizing the classical Hopf--Cole representation, we isolate the exact drift selected by the criterion and reorganize it in a form adapted to optimization. The key object is the conditional terminal law of the optimal process. We show that this law is a Gibbs measure for a proximally penalized energy, yielding three exact representations of the drift: potential, averaged-gradient, and barycentric. We then analyze two asymptotic regimes relevant for optimization. As terminal time is approached, the drift recovers a scaled gradient-descent field. In the low-temperature regime, assuming a unique global minimizer, the conditional terminal law concentrates on it even in the presence of nonglobal local minima, and the drift converges to an affine attraction field toward it. In the nondegenerate case we also derive Laplace asymptotics for the drift, the value function, and the covariance of the conditional terminal law. Finally, we record a simple gradient-free discretization suggested by the barycentric formula.
format Preprint
id arxiv_https___arxiv_org_abs_2605_24485
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Optimal drift optimizer for non-convex optimization
Li, Qin
Li, Sixu
Tadmor, Eitan
Trélat, Emmanuel
Optimization and Control
Analysis of PDEs
90C26, 35Q84, 49L20
We study a finite-horizon stochastic control criterion for non-convex optimization in which Brownian exploration is balanced against a quadratic control cost. Rather than emphasizing the classical Hopf--Cole representation, we isolate the exact drift selected by the criterion and reorganize it in a form adapted to optimization. The key object is the conditional terminal law of the optimal process. We show that this law is a Gibbs measure for a proximally penalized energy, yielding three exact representations of the drift: potential, averaged-gradient, and barycentric. We then analyze two asymptotic regimes relevant for optimization. As terminal time is approached, the drift recovers a scaled gradient-descent field. In the low-temperature regime, assuming a unique global minimizer, the conditional terminal law concentrates on it even in the presence of nonglobal local minima, and the drift converges to an affine attraction field toward it. In the nondegenerate case we also derive Laplace asymptotics for the drift, the value function, and the covariance of the conditional terminal law. Finally, we record a simple gradient-free discretization suggested by the barycentric formula.
title Optimal drift optimizer for non-convex optimization
topic Optimization and Control
Analysis of PDEs
90C26, 35Q84, 49L20
url https://arxiv.org/abs/2605.24485