A statistical physics approach to learning curves for the inverse Ising problem

DOI10.1088/1742-5468/aa727dzbMath1457.82055arXiv1705.05403OpenAlexW2614470710MaRDI QIDQ3303094

Ludovica Bachschmid-Romano, Manfred Opper

Publication date: 11 August 2020

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

Full work available at URL: https://arxiv.org/abs/1705.05403

Mathematics Subject Classification ID

Lattice systems (Ising, dimer, Potts, etc.) and systems on graphs arising in equilibrium statistical mechanics (82B20)

Related Items (3)

Ising model selection using ℓ ₁-regularized linear regression: a statistical mechanics analysis* ⋮ Structure learning in inverse Ising problems using ℓ ₂-regularized linear estimator ⋮ Learning performance in inverse Ising problems with sparse teacher couplings

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Statistical Mechanics of Learning
• A theory of solving TAP equations for Ising models with general invariant random matrices
• Learning of couplings for random asymmetric kinetic Ising models revisited: random correlation matrices and learning curves
• Small-correlation expansions for the inverse Ising problem
• Optimal generalization in perceptions
• Mean-field equations for spin models with orthogonal interaction matrices
• Statistical Physics of Spin Glasses and Information Processing
• Neural networks and physical systems with emergent collective computational abilities.

This page was built for publication: A statistical physics approach to learning curves for the inverse Ising problem