Deep Boltzmann Machines: Rigorous Results at Arbitrary Depth

Author:

Alberici DiegoORCID,Contucci Pierluigi,Mingione Emanuele

Abstract

AbstractA class of deep Boltzmann machines is considered in the simplified framework of a quenched system with Gaussian noise and independent entries. The quenched pressure of a K-layers spin glass model is studied allowing interactions only among consecutive layers. A lower bound for the pressure is found in terms of a convex combination of K Sherrington–Kirkpatrick models and used to study the annealed and replica symmetric regimes of the system. A map with a one-dimensional monomer–dimer system is identified and used to rigorously control the annealed region at arbitrary depth K with the methods introduced by Heilmann and Lieb. The compression of this high-noise region displays a remarkable phenomenon of localisation of the processing layers. Furthermore, a replica symmetric lower bound for the limiting quenched pressure of the model is obtained in a suitable region of the parameters and the replica symmetric pressure is proved to have a unique stationary point.

Funder

Università di Bologna

Ministero dell’Istruzione, dell’Università e della Ricerca

Publisher

Springer Science and Business Media LLC

Subject

Mathematical Physics,Nuclear and High Energy Physics,Statistical and Nonlinear Physics

Cited by 18 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Free Energy Fluctuations of the Bipartite Spherical SK Model at Critical Temperature;Annales Henri Poincaré;2024-05-27

2. Replica symmetry breaking in supervised and unsupervised Hebbian networks;Journal of Physics A: Mathematical and Theoretical;2024-04-09

3. Hopfield model with planted patterns: A teacher-student self-supervised learning model;Applied Mathematics and Computation;2023-12

4. Dense Hebbian neural networks: A replica symmetric picture of unsupervised learning;Physica A: Statistical Mechanics and its Applications;2023-10

5. Free energy upper bound for mean-field vector spin glasses;Annales de l'Institut Henri Poincaré, Probabilités et Statistiques;2023-08-01

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3