Learning Graphical Models From the Glauber Dynamics
In this paper, we consider the problem of learning undirected graphical models from data generated according to the Glauber dynamics (also known as the Gibbs sampler). The Glauber dynamics is a Markov chain that sequentially updates individual nodes (variables) in a graphical model and it is frequen...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2019
|
| Online Access: | http://hdl.handle.net/1721.1/120526 https://orcid.org/0000-0003-1303-582X https://orcid.org/0000-0001-8898-8778 https://orcid.org/0000-0003-0737-3259 |
| Summary: | In this paper, we consider the problem of learning undirected graphical models from data generated according to the Glauber dynamics (also known as the Gibbs sampler). 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 paper deviates from the standard formulation of graphical model learning in the literature, where one assumes access to independent identically distributed samples from the distribution. Much of the research on graphical model learning has been directed toward finding algorithms with low computational cost. As the main result of this paper, 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 2]log p, for a function f(d) defined explicitly in this paper, using nearly the information-Theoretic minimum number of samples. |
|---|