Deep Boltzmann machines: rigorous results at arbitrary depth

DOI10.1007/s00023-021-01027-2zbMath1469.82025arXiv2004.04495OpenAlexW3015748378MaRDI QIDQ2042343

Pierluigi Contucci, Diego Alberici, Emanuele Mingione

Publication date: 29 July 2021

Published in: Annales Henri Poincaré (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2004.04495

zbMATH Keywords

Gaussian noisespin glass modelBoltzmann machinesSherrington-Kirkpatrick models

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Neural networks for/in biological studies, artificial life and related topics (92B20) Statistical mechanics of random media, disordered materials (including liquid crystals and spin glasses) (82D30) Neural nets applied to problems in time-dependent statistical mechanics (82C32) Statistical mechanics of magnetic materials (82D40)

Related Items

Fluctuation results for multi-species Sherrington-Kirkpatrick model in the replica symmetric regime ⋮ Free energy in multi-species mixed \(p\)-spin spherical models ⋮ A transport equation approach for deep neural networks with quenched random weights ⋮ Thermodynamics of bidirectional associative memories ⋮ Dense Hebbian neural networks: a replica symmetric picture of unsupervised learning ⋮ Hopfield model with planted patterns: a teacher-student self-supervised learning model ⋮ Minimax formula for the replica symmetric free energy of deep restricted Boltzmann machines ⋮ Free energy upper bound for mean-field vector spin glasses ⋮ The solution of the deep Boltzmann machine on the Nishimori line ⋮ Learning and retrieval operational modes for three-layer restricted Boltzmann machines ⋮ Convergence of the free energy for spherical spin glasses

Cites Work

• Unnamed Item
• Free energy and complexity of spherical bipartite models
• Some properties of the phase diagram for mixed \(p\)-spin glasses
• Scaling limits for multi-species statistical mechanics mean-field models
• Some rigorous results on the Sherrington-Kirkpatrick spin glass model.
• Replica symmetry breaking in multi-species Sherrington-Kirkpatrick model
• The thermodynamic limit in mean field spin glass models
• Broken replica symmetry bounds in the mean field spin glass model
• Free energy of bipartite spherical Sherrington-Kirkpatrick model
• Annealing and replica-symmetry in deep Boltzmann machines
• Multi-species mean field spin glasses. Rigorous results
• Phase transition in the spiked random tensor with Rademacher prior
• The Parisi formula has a unique minimizer
• Theory of monomer-dimer systems
• An Efficient Learning Procedure for Deep Boltzmann Machines
• Equilibrium statistical mechanics of bipartite spin systems
• Bipartite Mean Field Spin Systems. Existence and Solution
• Perspectives on Spin Glasses
• Quadratic replica coupling in the Sherrington–Kirkpatrick mean field spin glass model
• The Sherrington-Kirkpatrick Model
• Mean Field Models for Spin Glasses
• The free energy in a multi-species Sherrington-Kirkpatrick model

This page was built for publication: Deep Boltzmann machines: rigorous results at arbitrary depth