Article

Swarm gradient dynamics for global optimization: the mean-field limit case

Jérôme Bolte, Laurent Miclo et Stéphane Villeneuve

Résumé

Using jointly geometric and stochastic reformulations of nonconvex problems and exploiting a Monge-Kantorovich gradient system formulation with vanishing forces, we formally extend the simulated annealing method to a wide class of global optimization methods. Due to an inbuilt combination of a gradient-like strategy and particles interactions, we call them swarm gradient dynamics. As in the original paper of Holley-Kusuoka- Stroock, the key to the existence of a schedule ensuring convergence to a global minimizer is a functional inequality. One of our central theoretical contributions is the proof of such an inequality for one-dimensional compact manifolds. We conjecture the inequality to be true in a much wider setting. We also describe a general method allowing for global optimization and evidencing the crucial role of functional inequalities à la Łojasiewicz.

Remplace

Jérôme Bolte, Laurent Miclo et Stéphane Villeneuve, « Swarm gradient dynamics for global optimization: the mean-field limit case », TSE Working Paper, n° 22-1302, mars 2022.

Référence

Jérôme Bolte, Laurent Miclo et Stéphane Villeneuve, « Swarm gradient dynamics for global optimization: the mean-field limit case », Mathematical Programming, vol. 205, mai 2024, p. 661–701.

Publié dans

Mathematical Programming, vol. 205, mai 2024, p. 661–701