Data-driven learning of the generalized Langevin equation with state-dependent memory

TL;DR

This paper introduces a data-driven approach to learn stochastic reduced models with state-dependent memory, extending the generalized Langevin equation to better capture complex system dynamics.

Contribution

It develops a novel method to incorporate state-dependent memory into GLE-based models, improving the accuracy of molecular kinetics predictions.

Findings

Standard GLE limitations highlighted

State-dependency improves prediction accuracy

Model captures heterogeneous energy dissipation

Abstract

We present a data-driven method to learn stochastic reduced models of complex systems that retain a state-dependent memory beyond the standard generalized Langevin equation (GLE) with a homogeneous kernel. The constructed model naturally encodes the heterogeneous energy dissipation by jointly learning a set of state features and the non-Markovian coupling among the features. Numerical results demonstrate the limitation of the standard GLE and the essential role of the broadly overlooked state-dependency nature in predicting molecule kinetics related to conformation relaxation and transition.