Critical properties of the SAT/UNSAT transitions in the classification problem of structured data

DOI10.1088/1742-5468/ac312bOpenAlexW3209628551WikidataQ114634528 ScholiaQ114634528MaRDI QIDQ5860321

Mauro Pastore

Publication date: 19 November 2021

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

Full work available at URL: https://arxiv.org/abs/2109.08502

zbMATH Keywords

machine learningcavity and replica method

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Uses Software

• QCQP

Cites Work

• Unnamed Item
• Techniques of replica symmetry breaking and the storage problem of the McCulloch-Pitts neuron
• Statistical Mechanics of Learning
• Statistical Learning Theory: Models, Concepts, and Results
• Storage of correlated patterns in a perceptron
• The simplest model of jamming
• Structural risk minimization over data-dependent hierarchies
• Generalization from correlated sets of patterns in the perceptron
• Theory of Simple Glasses
• Determining computational complexity from characteristic ‘phase transitions’
• Advanced Lectures on Machine Learning
• The space of interactions in neural network models
• Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition
• Statistical mechanics methods and phase transitions in optimization problems

This page was built for publication: Critical properties of the SAT/UNSAT transitions in the classification problem of structured data