Bolte, JérômeORCID: https://orcid.org/0000-0002-1676-8407, Miclo, LaurentORCID: https://orcid.org/0000-0001-5502-2862 and Villeneuve, StéphaneORCID: https://orcid.org/0000-0003-3213-1905 (2024) Swarm gradient dynamics for global optimization: the mean-field limit case. Mathematical Programming, Vol. 205. pp. 661-701.

Preview

Text Download (629kB) | Preview

Abstract

Using jointly geometric and stochastic reformulations of nonconvex problems and exploiting a Monge–Kantorovich (or Wasserstein) gradient system formulation with vanishing forces, we formally extend the simulated annealing method to a wide range of global optimization methods. Due to the built-in combination of a gradient-like strategy and particle interactions, we call them swarm gradient dynamics. As in the original paper by Holley–Kusuoka–Stroock, a functional inequality is the key to the existence of a schedule that ensures convergence to a global minimizer. One of our central theoretical contributions is proving such an inequality for one-dimensional compact manifolds. We conjecture that the inequality holds true in a much broader setting. Additionally, we describe a general method for global optimization that highlights the essential role of functional inequalities la Łojasiewicz.

Available Versions of this Item

• Swarm gradient dynamics for global optimization: the mean-field limit case. (deposited 09 Feb 2022 13:25)
  • Swarm gradient dynamics for global optimization: the mean-field limit case. (deposited 25 May 2023 07:06) [Currently Displayed]