Some Remarks on Replicated Simulated Annealing - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Journal of Statistical Physics Année : 2021

Some Remarks on Replicated Simulated Annealing

Résumé

Recently authors have introduced the idea of training discrete weights neural networks using a mix between classical simulated annealing and a replica ansatz known from the statistical physics literature. Among other points, they claim their method is able to find robust configurations. In this paper, we analyze this so called “replicated simulated annealing” algorithm. In particular, we give criteria to guarantee its convergence, and study when it successfully samples from configurations. We also perform experiments using synthetic and real data bases.
Fichier principal
Vignette du fichier
Gripon2021_Article_SomeRemarksOnReplicatedSimulat.pdf (622.62 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03238781 , version 1 (31-05-2021)

Licence

Paternité

Identifiants

Citer

Vincent Gripon, Matthias Löwe, Franck Vermet. Some Remarks on Replicated Simulated Annealing. Journal of Statistical Physics, 2021, 182 (3), ⟨10.1007/s10955-021-02727-z⟩. ⟨hal-03238781⟩
42 Consultations
54 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More