On the equivalence between the Kinetic Ising Model and discrete autoregressive processes

TL;DR

This paper proves a rigorous equivalence between the Kinetic Ising Model and discrete autoregressive processes, showing they describe binary time series with maximum entropy and enabling cross-application of inference methods.

Contribution

It establishes a formal, invertible mapping between the two models, providing theoretical justification and practical tools for analyzing binary time series.

Findings

Proved the equivalence between the Kinetic Ising Model and discrete autoregressive processes.

Showed both models maximize entropy given certain statistical constraints.

Enabled transfer of inference techniques between the two models.

Abstract

Binary random variables are the building blocks used to describe a large variety of systems, from magnetic spins to financial time series and neuron activity. In Statistical Physics the Kinetic Ising Model has been introduced to describe the dynamics of the magnetic moments of a spin lattice, while in time series analysis discrete autoregressive processes have been designed to capture the multivariate dependence structure across binary time series. In this article we provide a rigorous proof of the equivalence between the two models in the range of a unique and invertible map unambiguously linking one model parameters set to the other. Our result finds further justification acknowledging that both models provide maximum entropy distributions of binary time series with given means, auto-correlations, and lagged cross-correlations of order one. We further show that the equivalence between the two models permits to exploit the inference methods originally developed for one model in the inference of the other.