Adaptive Cluster Expansion for Inferring Boltzmann Machines with Noisy Data
Data Analysis, Statistics and Probability
2015-05-27 v1 Statistical Mechanics
Machine Learning
Neurons and Cognition
Quantitative Methods
Abstract
We introduce a procedure to infer the interactions among a set of binary variables, based on their sampled frequencies and pairwise correlations. The algorithm builds the clusters of variables contributing most to the entropy of the inferred Ising model, and rejects the small contributions due to the sampling noise. Our procedure successfully recovers benchmark Ising models even at criticality and in the low temperature phase, and is applied to neurobiological data.
Cite
@article{arxiv.1102.3260,
title = {Adaptive Cluster Expansion for Inferring Boltzmann Machines with Noisy Data},
author = {Simona Cocco and Rémi Monasson},
journal= {arXiv preprint arXiv:1102.3260},
year = {2015}
}
Comments
Accepted for publication in Physical Review Letters (2011)