SpReME: Sparse Regression for Multi-Environment Dynamic Systems

TL;DR

SpReME is a sparse regression method that identifies shared dynamical structures across multiple environments while allowing environment-specific variations, improving the discovery and prediction of underlying system dynamics.

Contribution

The paper introduces SpReME, a novel sparse regression approach that captures common dynamics across environments with environment-specific coefficients, enhancing multi-environment system modeling.

Findings

Successfully captures correct dynamics in four different systems.

Improves prediction performance over existing methods.

Effectively models shared and environment-specific dynamics.

Abstract

Learning dynamical systems is a promising avenue for scientific discoveries. However, capturing the governing dynamics in multiple environments still remains a challenge: model-based approaches rely on the fidelity of assumptions made for a single environment, whereas data-driven approaches based on neural networks are often fragile on extrapolating into the future. In this work, we develop a method of sparse regression dubbed SpReME to discover the major dynamics that underlie multiple environments. Specifically, SpReME shares a sparse structure of ordinary differential equation (ODE) across different environments in common while allowing each environment to keep the coefficients of ODE terms independently. We demonstrate that the proposed model captures the correct dynamics from multiple environments over four different dynamic systems with improved prediction performance.