Learning to Sample from Censored Markov Random Fields
Machine Learning
2021-01-18 v1
Abstract
We study learning Censor Markov Random Fields (abbreviated CMRFs). These are Markov Random Fields where some of the nodes are censored (not observed). We present an algorithm for learning high-temperature CMRFs within o(n) transportation distance. Crucially our algorithm makes no assumption about the structure of the graph or the number or location of the observed nodes. We obtain stronger results for high girth high-temperature CMRFs as well as computational lower bounds indicating that our results can not be qualitatively improved.
Cite
@article{arxiv.2101.06178,
title = {Learning to Sample from Censored Markov Random Fields},
author = {Ankur Moitra and Elchanan Mossel and Colin Sandon},
journal= {arXiv preprint arXiv:2101.06178},
year = {2021}
}