Topology Inference for Network Systems: Causality Perspective and Non-asymptotic Performance

TL;DR

This paper introduces a causality-based topology inference method for network systems using noisy single-trajectory data, providing non-asymptotic performance analysis, online implementation, and extensions to nonlinear dynamics, with empirical validation.

Contribution

It proposes a novel causality-based inference approach with non-asymptotic guarantees, online adaptation, and extensions to nonlinear systems, advancing the state-of-the-art in network topology inference.

Findings

The method achieves zero inference error asymptotically.

It outperforms existing algorithms in accuracy and efficiency.

The approach is effective for both linear and nonlinear network systems.

Abstract

Topology inference for network systems (NSs) plays a crucial role in many areas. This paper advocates a causality-based method based on noisy observations from a single trajectory of a NS, which is represented by the state-space model with general directed topology. Specifically, we first prove its close relationships with the ideal Granger estimator for multiple trajectories and the traditional ordinary least squares (OLS) estimator for a single trajectory. Along with this line, we analyze the non-asymptotic inference performance of the proposed method by taking the OLS estimator as a reference, covering both asymptotically and marginally stable systems. The derived convergence rates and accuracy results suggest the proposed method has better performance in addressing potentially correlated observations and achieves zero inference error asymptotically. Besides, an online/recursive version of our method is established for efficient computation or time-varying cases. Extensions on NSs with nonlinear dynamics are also discussed. Comprehensive tests corroborate the theoretical findings and comparisons with other algorithms highlight the superiority of the proposed method.