Some Remarks on Replicated Simulated Annealing
Machine Learning
2021-03-17 v2 Neural and Evolutionary Computing
Optimization and Control
Probability
Machine Learning
Abstract
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 explicit criteria to guarantee its convergence, and study when it successfully samples from configurations. We also perform experiments using synthetic and real data bases.
Cite
@article{arxiv.2009.14702,
title = {Some Remarks on Replicated Simulated Annealing},
author = {Vincent Gripon and Matthias Löwe and Franck Vermet},
journal= {arXiv preprint arXiv:2009.14702},
year = {2021}
}