Exponential Reduction in Sample Complexity with Learning of Ising Model Dynamics

Andrey Y. Lokhov; Arkopal Dutt; Marc Vuffray; Sidhant Misra

Exponential Reduction in Sample Complexity with Learning of Ising Model Dynamics

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2104.00995 v2 pith:HLNJDFYF submitted 2021-04-02 cs.LG cond-mat.stat-mechphysics.data-anstat.ML

Exponential Reduction in Sample Complexity with Learning of Ising Model Dynamics

Arkopal Dutt , Andrey Y. Lokhov , Marc Vuffray , Sidhant Misra This is my paper

classification cs.LG cond-mat.stat-mechphysics.data-anstat.ML

keywords samplescomplexitydynamicalprocesssamplegraphicallearningmany

verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

0 comments

read the original abstract

The usual setting for learning the structure and parameters of a graphical model assumes the availability of independent samples produced from the corresponding multivariate probability distribution. However, for many models the mixing time of the respective Markov chain can be very large and i.i.d. samples may not be obtained. We study the problem of reconstructing binary graphical models from correlated samples produced by a dynamical process, which is natural in many applications. We analyze the sample complexity of two estimators that are based on the interaction screening objective and the conditional likelihood loss. We observe that for samples coming from a dynamical process far from equilibrium, the sample complexity reduces exponentially compared to a dynamical process that mixes quickly.

discussion (0)

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

Mixing-Free and Signal-Optimal Learning of Gaussian Graphical Models from Glauber Dynamics
stat.ML 2026-07 accept novelty 7.0

Exact graph recovery from one Glauber trajectory is provably achievable at the information-theoretic κ^{-2} sample rate without mixing or stationarity assumptions, via a dueling-neighborhood search with two local traj...