A deep learning approach to the measurement of long-lived memory kernels from Generalised Langevin Dynamics

Abstract

Memory effects are ubiquitous in a wide variety of complex physical phenomena, ranging from glassy dynamics and metamaterials to climate models. The Generalised Langevin Equation (GLE) provides a rigorous way to describe memory effects via the so-called memory kernel in an integro-differential equation. However, the memory kernel is often unknown, and accurately predicting or measuring it via e.g. a numerical inverse Laplace transform remains a herculean task. Here we describe a novel method using deep neural networks (DNNs) to measure memory kernels from dynamical data. As proof-of-principle, we focus on the notoriously long-lived memory effects of glassy systems, which have proved a major challenge to existing methods. Specifically, we learn a training set generated with the Mode-Coupling Theory (MCT) of hard spheres. Our DNNs are remarkably robust against noise, in contrast to conventional techniques which require ensemble averaging over many independent trajectories. Finally, we demonstrate that a network trained on data generated from analytic theory (hard-sphere MCT) generalises well to data from simulations of a different system (Brownian Weeks-Chandler-Andersen particles). We provide a general pipeline, KernelLearner, for training networks to extract memory kernels from any non-Markovian system described by a GLE. The success of our DNN method applied to glassy systems suggests deep learning can play an important role in the study of dynamical systems that exhibit memory effects.

References in corpus (28)

• Adam: A Method for Stochastic Optimization
• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• Mode-Coupling Theory (MCT) Lecture Notes
• Mode-Coupling Theory of the Glass Transition: A Primer
• Stochastic Climate Theory and Modelling
• Review of Inverse Laplace Transform Algorithms for Laplace-Space Numerical Approaches
• Autonomously revealing hidden local structures in supercooled liquids
• Iterative Reconstruction of Memory Kernels
• Artificial Neural Network Approach to the Analytic Continuation Problem
• Colloidal glass transition: Beyond mode-coupling theory
• Generalized Quantum Master Equations In and Out of Equilibrium: When Can One Win?
• Microscopic dynamics of supercooled liquids from first principles
• Assessing the structural heterogeneity of supercooled liquids through community inference
• Predicting dynamic heterogeneity in glass-forming liquids by physics-inspired machine learning
• Memory embedded non-intrusive reduced order modeling of non-ergodic flows
• A Priori Estimation Of Memory Effects In Coarse-Grained Nonlinear Systems Using The Mori-Zwanzig Formalism
• Efficient construction of generalized master equation memory kernels for multi-state systems from nonadiabatic quantum-classical dynamics
• Data-driven molecular modeling with the generalized Langevin equation
• Machine learning many-body potentials for colloidal systems
• BOTAN: BOnd TArgeting Network for prediction of slow glassy dynamics by machine learning relative motion
• Dimensionality reduction of local structure in glassy binary mixtures
• Memory functions reveal structural properties of gene regulatory networks
• On the Generalization Benefit of Noise in Stochastic Gradient Descent
• On mean-field theories of dynamics in supercooled liquids
• Data-driven construction of stochastic reduced dynamics encoded with non-Markovian features
• Generalized mode-coupling theory of the glass transition. II. Analytical scaling laws
• The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study
• Generalized Mode-Coupling Theory for Mixtures of Brownian Particles