MINIMAX FORMULA FOR THE REPLICA SYMMETRIC FREE ENERGY OF DEEP RESTRICTED BOLTZMANN MACHINES
成果类型：
Article
署名作者：
Genovese, Giuseppe
署名单位：
University of Zurich
刊物名称：
ANNALS OF APPLIED PROBABILITY
ISSN/ISSBN：
1050-5164
DOI：
10.1214/22-AAP1868
发表日期：
2023
页码：
2324-2341
关键词：
摘要：
We study the free energy of a most used deep architecture for restricted Boltzmann machines, where the layers are disposed in series. Assuming inde-pendent Gaussian distributed random weights, we show that the error term in the so-called replica symmetric sum rule can be optimised as a saddle point. This leads us to conjecture that in the replica symmetric approximation the free energy is given by a min max formula, which parallels the one achieved for case.
来源URL：