Learning the Influence Graph of a High-Dimensional Markov Process with Memory

TL;DR

This paper develops a method to learn the influence graph of high-dimensional Markov processes with memory, using binary string observations and proving logarithmic sample complexity under certain conditions.

Contribution

It extends existing algorithms for i.i.d. models to Markov processes with memory and provides theoretical guarantees on sample complexity.

Findings

Logarithmic sample complexity for influence graph learning.

Extension of graphical model learning algorithms to Markov processes with memory.

Derivation of convergence bounds for the observed process to stationary distribution.

Abstract

Motivated by multiple applications in social networks, nervous systems, and financial risk analysis, we consider the problem of learning the underlying (directed) influence graph or causal graph of a high-dimensional multivariate discrete-time Markov process with memory. At any discrete time instant, each observed variable of the multivariate process is a binary string of random length, which is parameterized by an unobservable or hidden [0,1]-valued scalar. The hidden scalars corresponding to the variables evolve according to discrete-time linear stochastic dynamics dictated by the underlying influence graph whose nodes are the variables. We extend an existing algorithm for learning i.i.d. graphical models to this Markovian setting with memory and prove that it can learn the influence graph based on the binary observations using logarithmic (in number of variables or nodes) samples when the degree of the influence graph is bounded. The crucial analytical contribution of this work is the derivation of the sample complexity result by upper and lower bounding the rate of convergence of the observed Markov process with memory to its stationary distribution in terms of the parameters of the influence graph.