Learning graphical models from the Glauber dynamics
This addresses the challenge of learning graphical models from sequential, non-i.i.d. data, which is incremental as it adapts existing methods to a different sampling scenario.
The paper tackles the problem of learning undirected graphical models from data generated by the Glauber dynamics, rather than from i.i.d. samples, and shows that binary pairwise models can be reconstructed in time f(d)p^2 log p with nearly the information-theoretic minimum samples.
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 $f(d)p^2\log p$, for a function $f(d)$, using nearly the information-theoretic minimum number of samples.