Learning interaction kernels in heterogeneous systems of agents from multiple trajectories

TL;DR

This paper develops a nonparametric method to learn interaction laws in heterogeneous multi-agent systems from multiple trajectories, providing theoretical guarantees, an efficient algorithm, and demonstrating robustness and accuracy through simulations.

Contribution

It introduces a learnability condition, constructs convergent estimators at optimal rates, and proposes a scalable least squares algorithm for high-dimensional data.

Findings

Estimators converge at the optimal min-max rate for 1D nonparametric regression.

The learnability condition is satisfied in practical models.

Estimators are robust to noise and accurately predict dynamics over large time intervals.

Abstract

Systems of interacting particles or agents have wide applications in many disciplines such as Physics, Chemistry, Biology and Economics. These systems are governed by interaction laws, which are often unknown: estimating them from observation data is a fundamental task that can provide meaningful insights and accurate predictions of the behaviour of the agents. In this paper, we consider the inverse problem of learning interaction laws given data from multiple trajectories, in a nonparametric fashion, when the interaction kernels depend on pairwise distances. We establish a condition for learnability of interaction kernels, and construct estimators that are guaranteed to converge in a suitable $L^2$ space, at the optimal min-max rate for 1-dimensional nonparametric regression. We propose an efficient learning algorithm based on least squares, which can be implemented in parallel for multiple trajectories and is therefore well-suited for the high dimensional, big data regime. Numerical simulations on a variety examples, including opinion dynamics, predator-swarm dynamics and heterogeneous particle dynamics, suggest that the learnability condition is satisfied in models used in practice, and the rate of convergence of our estimator is consistent with the theory. These simulations also suggest that our estimators are robust to noise in the observations, and produce accurate predictions of dynamics in relative large time intervals, even when they are learned from data collected in short time intervals.