Clustering of solutions in the symmetric binary perceptron

DOI10.1088/1742-5468/ab99bezbMath1459.82249arXiv1911.06756OpenAlexW3101341788MaRDI QIDQ5854146

Carlo Baldassi, Carlo Lucibello, Riccardo Zecchina, Riccardo della Vecchia

Publication date: 16 March 2021

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

Full work available at URL: https://arxiv.org/abs/1911.06756

zbMATH Keywords

neural networksfirst and second moment methodenergy landscapescavity and replica method

Mathematics Subject Classification ID

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)

Cites Work

• Generalization learning in a perceptron with binary synapses
• Pairs of SAT-assignments in random Boolean formulæ
• Statistical Mechanics of Learning
• Entropy landscape of solutions in the binary perceptron problem
• A Max-Sum algorithm for training discrete neural networks
• Local entropy as a measure for sampling solutions in constraint satisfaction problems
• Storage capacity in symmetric binary perceptrons
• Capacity lower bound for the Ising perceptron
• Shaping the learning landscape in neural networks around wide flat minima