Exponential Reduction in Sample Complexity with Learning of Ising Model Dynamics

by   Arkopal Dutt, et al.

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.



There are no comments yet.


page 1

page 2

page 3

page 4


Learning graphical models from the Glauber dynamics

In this paper we consider the problem of learning undirected graphical m...

Learning Continuous Exponential Families Beyond Gaussian

We address the problem of learning of continuous exponential family dist...

Efficient Learning of Discrete Graphical Models

Graphical models are useful tools for describing structured high-dimensi...

A Brief Study of In-Domain Transfer and Learning from Fewer Samples using A Few Simple Priors

Domain knowledge can often be encoded in the structure of a network, suc...

Learning of Discrete Graphical Models with Neural Networks

Graphical models are widely used in science to represent joint probabili...

Statistical Windows in Testing for the Initial Distribution of a Reversible Markov Chain

We study the problem of hypothesis testing between two discrete distribu...

Learning Ising Models with Independent Failures

We give the first efficient algorithm for learning the structure of an I...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.