Efficiently Learning Ising Models on Arbitrary Graphs
Name
Bresler_Efficiently learning Ising models.pdf
Size
268.33 KB
Format
Adobe PDF
Checksum (MD5)
7d791cb0427671b2726470ac0760bf9a
Author(s)
Bresler, Guy
Date Issued
June 2015
Journal
Proceedings of the Forty-Seventh Annual ACM on Symposium on Theory of Computing - STOC '15
Publisher
Association for Computing Machinery (ACM)
Citation
Bresler, Guy. “Efficiently Learning Ising Models on Arbitrary Graphs.” ACM Press, Forty-Seventh Annual ACM on Symposium on Theory of Computing - STOC '15, Portand, Oregon, USA, 14-17 Junes, 2015. Association for Computing Machinery (ACM), 2015, pp. 771–782.
Version
Original manuscript
Abstract
We consider the problem of reconstructing the graph underlying an Ising model from i.i.d. samples. Over the last fifteen years this problem has been of significant interest in the statistics, machine learning, and statistical physics communities, and much of the effort has been directed towards finding algorithms with low computational cost for various restricted classes of models. Nevertheless, for learning Ising models on general graphs with p nodes of degree at most d, it is not known whether or not it is possible to improve upon the p[superscript d] computation needed to exhaustively search over all possible neighborhoods for each node. In this paper we show that a simple greedy procedure allows to learn the structure of an Ising model on an arbitrary bounded-degree graph in time on the order of p[superscript 2]. We make no assumptions on the parameters except what is necessary for identifiability of the model, and in particular the results hold at low-temperatures as well as for highly non-uniform models. The proof rests on a new structural property of Ising models: we show that for any node there exists at least one neighbor with which it has a high mutual information. This structural property may be of independent interest.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/2746539.2746631
