Learning graphical models from the Glauber dynamics
Name
Gamarnik_Learning graphical.pdf
Size
206.67 KB
Format
Adobe PDF
Checksum (MD5)
1d7af7179d1ccca5465c535f760614a5
Author(s)
Bresler, Guy
Gamarnik, David
Shah, Devavrat
Date Issued
September 2014
Journal
Proceedings of the 2014 52nd Annual Allerton Conference on Communication, Control, and Computing (Allerton)
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Bresler, Guy, David Gamarnik, and Devavrat Shah. “Learning Graphical Models from the Glauber Dynamics.” 2014 52nd Annual Allerton Conference on Communication, Control, and Computing (Allerton) (September 2014).
Version
Author's final manuscript
Abstract
In this paper we consider the problem of learning undirected graphical models from data generated according to the Glauber dynamics. The Glauber dynamics is a Markov chain that sequentially updates individual nodes (variables) in a graphical model and it is frequently used to sample from the stationary distribution (to which it converges given sufficient time). Additionally, the Glauber dynamics is a natural dynamical model in a variety of settings. This work deviates from the standard formulation of graphical model learning in the literature, where one assumes access to i.i.d. samples from the distribution. Much of the research on graphical model learning has been directed towards finding algorithms with low computational cost. As the main result of this work, we establish that the problem of reconstructing binary pairwise graphical models is computationally tractable when we observe the Glauber dynamics. Specifically, we show that a binary pairwise graphical model on p nodes with maximum degree d can be learned in time f(d)p[superscript 3] log p, for a function f(d), using nearly the information-theoretic minimum possible number of samples. There is no known algorithm of comparable efficiency for learning arbitrary binary pairwise models from i.i.d. samples.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Sloan School of Management
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/ALLERTON.2014.7028584
