Saved in:
Bibliographic Details
Main Author: Luo, Kaiming
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.13708
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918249535373312
author Luo, Kaiming
author_facet Luo, Kaiming
contents The interaction structure of a complex dynamical system governs its collective behavior, yet existing reconstruction methods struggle with nonlinear, heterogeneous, and higher-order couplings, especially when only steady states are observable. We propose a Variational Physics-Informed Ansatz (VPIA) that infers general interaction operators directly from heterogeneous steady-state data. VPIA embeds the steady-state constraints of the dynamics into a differentiable variational representation and reconstructs the underlying couplings by minimizing a physics-derived steady-state residual, without requiring temporal trajectories, derivative estimation, or supervision. Residual sampling combined with natural-gradient optimization enables scalable learning of large and higher-order networks. Across diverse nonlinear systems, VPIA accurately recovers directed, weighted, and multi-body structures under substantial noise, providing a unified and robust framework for physics-constrained inference of complex interaction networks in settings where only snapshot observations are available.
format Preprint
id arxiv_https___arxiv_org_abs_2512_13708
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Variational Physics-Informed Ansatz for Reconstructing Hidden Interaction Networks from Steady States
Luo, Kaiming
Machine Learning
The interaction structure of a complex dynamical system governs its collective behavior, yet existing reconstruction methods struggle with nonlinear, heterogeneous, and higher-order couplings, especially when only steady states are observable. We propose a Variational Physics-Informed Ansatz (VPIA) that infers general interaction operators directly from heterogeneous steady-state data. VPIA embeds the steady-state constraints of the dynamics into a differentiable variational representation and reconstructs the underlying couplings by minimizing a physics-derived steady-state residual, without requiring temporal trajectories, derivative estimation, or supervision. Residual sampling combined with natural-gradient optimization enables scalable learning of large and higher-order networks. Across diverse nonlinear systems, VPIA accurately recovers directed, weighted, and multi-body structures under substantial noise, providing a unified and robust framework for physics-constrained inference of complex interaction networks in settings where only snapshot observations are available.
title Variational Physics-Informed Ansatz for Reconstructing Hidden Interaction Networks from Steady States
topic Machine Learning
url https://arxiv.org/abs/2512.13708