Adaptive simulated annealing through alternating Renyi divergence minimization - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Adaptive simulated annealing through alternating Renyi divergence minimization

Résumé

Simulated annealing is a popular approach to solve nonconvex and black-box optimization problems. It consists in running a non-homogeneous Markov chain to sample from a sequence of Boltzmann probability distributions. This sequence is controlled by a cooling schedule, which governs the concentration of the mass of the Boltzmann distributions around the global minimizers. However, convergence is often slow, difficult to assess, and requires a fixed cooling schedule. We propose here a new simulated annealing algorithm with adaptive cooling schedule, which draws samples from variational approximations of the Boltzmann distributions. Our approach is theoretically sound and relies on an alternating Bregman proximal-gradient scheme minimizing a regularized Rényi divergence. Numerical experiments illustrate the performance of the method.
Fichier principal
Vignette du fichier
ICASSP_2023__revised_version_.pdf (302.3 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04094489 , version 1 (11-05-2023)

Identifiants

Citer

Thomas Guilmeau, Emilie Chouzenoux, Víctor Elvira. Adaptive simulated annealing through alternating Renyi divergence minimization. ICASSP 2023 - IEEE International Conference on Acoustics, Speech and Signal Processing, Jun 2023, Rhodes (Grèce), Greece. ⟨10.1109/ICASSP49357.2023.10096619⟩. ⟨hal-04094489⟩
48 Consultations
25 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More