A dynamical mean-field theory for learning in restricted Boltzmann machines

DOI10.1088/1742-5468/abb8c9zbMath1459.82167arXiv2005.01560OpenAlexW3095006753MaRDI QIDQ5857421

Burak Çakmak, Manfred Opper

Publication date: 1 April 2021

Published in: Journal of Statistical Mechanics: Theory and Experiment (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2005.01560

zbMATH Keywords

spin glassesmachine learningmessage-passing algorithmscavity and replica method

Mathematics Subject Classification ID

Interacting particle systems in time-dependent statistical mechanics (82C22)

Related Items (2)

Approximate message passing algorithms for rotationally invariant matrices ⋮ Analysis of random sequential message passing algorithms for approximate inference

Cites Work

• Unnamed Item
• Unnamed Item
• An iterative construction of solutions of the TAP equations for the Sherrington-Kirkpatrick model
• Rectangular \(R\)-transform as the limit of rectangular spherical integrals
• New scaling of Itzykson-Zuber integrals
• Thermodynamics of restricted Boltzmann machines and related learning dynamics
• Integration of invariant matrices and moments of inverses of Ginibre and Wishart matrices
• Random Matrix Methods for Wireless Communications
• A theory of solving TAP equations for Ising models with general invariant random matrices
• Training Products of Experts by Minimizing Contrastive Divergence
• Information, Physics, and Computation
• New method for studying the dynamics of disordered spin systems without finite-size effects
• Introduction to Random Matrices
• The planar approximation. II
• Statistical Physics of Spin Glasses and Information Processing
• Mean-field inference methods for neural networks
• Analysis of Bayesian inference algorithms by the dynamical functional approach
• Vector Approximate Message Passing
• Rigorous Dynamics of Expectation-Propagation-Based Signal Recovery from Unitarily Invariant Measurements
• The Dynamics of Message Passing on Dense Graphs, with Applications to Compressed Sensing
• The space of interactions in neural network models
• High-temperature expansions and message passing algorithms

This page was built for publication: A dynamical mean-field theory for learning in restricted Boltzmann machines