Ubiquitous power law scaling in nonlinear self-excited Hawkes processes

TL;DR

This paper introduces a class of nonlinear self-excited Hawkes processes that naturally produce power law distributions in their intensities, offering a new mechanism for understanding the ubiquity of such distributions including Zipf's law across various systems.

Contribution

It combines nonlinear Hawkes processes with activation dynamics to explain the emergence of power law tails in their intensity distributions, including Zipf's law.

Findings

Power law distributions arise under specific conditions in nonlinear Hawkes processes.

Zipf's law emerges when the average mark tends to zero.

The mechanism explains the ubiquity of power laws in natural and social systems.

Abstract

The origin(s) of the ubiquity of probability distribution functions (PDF) with power law tails is still a matter of fascination and investigation in many scientific fields from linguistic, social, economic, computer sciences to essentially all natural sciences. In parallel, self-excited dynamics is a prevalent characteristic of many systems, from the physics of shot noise and intermittent processes, to seismicity, financial and social systems. Motivated by activation processes of the Arrhenius form, we bring the two threads together by introducing a general class of nonlinear self-excited point processes with fast-accelerating intensities as a function of "tension". Solving the corresponding master equations, we find that a wide class of such nonlinear Hawkes processes have the PDF of their intensities described by a power law on the condition that (i) the intensity is a fast-accelerating function of tension, (ii) the distribution of marks is two-sided with non-positive mean, and (iii) it has fast-decaying tails. In particular, Zipf's scaling is obtained in the limit where the average mark is vanishing. This unearths a novel mechanism for power laws including Zipf's law, providing a new understanding of their ubiquity.