Free energies of Boltzmann machines: self-averaging, annealed and replica symmetric approximations in the thermodynamic limit

DOI10.1088/1742-5468/ab02efOpenAlexW3102055153MaRDI QIDQ5006959

Brunello Tirozzi, Adriano Barra, Elena Agliari

Publication date: 17 August 2021

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

Full work available at URL: https://arxiv.org/abs/1810.11075

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Related Items (8)

Nonlinear PDEs approach to statistical mechanics of dense associative memories ⋮ A transport equation approach for deep neural networks with quenched random weights ⋮ Dreaming neural networks: rigorous results ⋮ Generalized Guerra's interpolation schemes for dense associative neural networks ⋮ The relativistic Hopfield model with correlated patterns ⋮ Learning and retrieval operational modes for three-layer restricted Boltzmann machines ⋮ Replica symmetry breaking in neural networks: a few steps toward rigorous results ⋮ Replica analysis of the lattice-gas restricted Boltzmann machine partition function

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Optimization by Simulated Annealing
• Anergy in self-directed B lymphocytes: a statistical mechanics perspective
• ``Neural computation of decisions in optimization problems
• Gibbs states of the Hopfield model in the regime of perfect memory
• Rigorous results for the Hopfield model with many patterns
• Gibbs states of the Hopfield model with extensively many patterns.
• A thermodynamic perspective of immune capabilities
• On the stability of the quenched state in mean-field spin-glass models
• The thermodynamic limit in mean field spin glass models
• Rigorous solution of the Gardner problem
• Broken replica symmetry bounds in the mean field spin glass model
• Exponential inequalities and convergence of moments in the replica-symmetric regime of the Hopfield model.
• The replica-symmetric solution without replica trick for the Hopfield model
• Concentration of measure and isoperimetric inequalities in product spaces
• On the equivalence of Hopfield networks and Boltzmann machines
• Non-convex multi-species Hopfield models
• Thermodynamics of restricted Boltzmann machines and related learning dynamics
• Multi-species mean field spin glasses. Rigorous results
• The free energy of a class of Hopfield models
• Universality in bipartite mean field spin glasses
• Statistical mechanics of clonal expansion in lymphocyte networks modelled with slow and fast variables
• Equilibrium statistical mechanics of bipartite spin systems
• A dynamical model of the adaptive immune system: effects of cells promiscuity, antigens and B–B interactions
• The role of idiotypic interactions in the adaptive immune system: a belief-propagation approach
• Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
• General properties of overlap probability distributions in disordered spin systems. Towards Parisi ultrametricity
• Modeling Brain Function
• On the replica symmetric equations for the Hopfield model
• Statistical Physics of Spin Glasses and Information Processing
• The Sherrington-Kirkpatrick Model
• Neural networks and physical systems with emergent collective computational abilities.
• Statistical Mechanics of Disordered Systems
• Martingale Central Limit Theorems
• The replica symmetric approximation of the analogical neural network

This page was built for publication: Free energies of Boltzmann machines: self-averaging, annealed and replica symmetric approximations in the thermodynamic limit