Replica method for computational problems with randomness: principles and illustrations

DOI10.1088/1742-5468/AD292DMaRDI QIDQ7232402zbMATH OpenFDO

Authors Urte Adomaityte, Alberto Fachechi, Pierre Mergny, Damien Barbier, R. Monasson, J. Steinberg

Publication date 23 April 2026

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

Full work available at URL https://doi.org/10.1088/1742-5468/AD292D

zbMATH Keywords

machine learningnetworksrandom graphsspin glassescavity and replica method

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Cites work

• A Gaussian scenario for unsupervised learning
• Enumeration of Seven-Argument Threshold Functions
• Large Deviations of Extreme Eigenvalues of Random Matrices
• Learning compositional representations of interacting systems with restricted Boltzmann machines: comparative study of lattice proteins
• Modeling Brain Function
• On Information and Sufficiency
• On the equivalence of Hopfield networks and Boltzmann machines
• Optimal unsupervised learning
• Parallel retrieval of correlated patterns: from Hopfield networks to Boltzmann machines
• Reducing the Dimensionality of Data with Neural Networks
• Spin-glass theory for pedestrians
• Statistical mechanics methods and phase transitions in optimization problems
• Statistical mechanics of learning
• The Parisi formula
• Thermodynamics of restricted Boltzmann machines and related learning dynamics
• Training Products of Experts by Minimizing Contrastive Divergence
• Training restricted Boltzmann machines: an introduction
• ‘Place-cell’ emergence and learning of invariant data with restricted Boltzmann machines: breaking and dynamical restoration of continuous symmetries in the weight space

This page was built for publication: Replica method for computational problems with randomness: principles and illustrations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7232402)