PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
Synapse
⌘+K
Synapse
August 22, 2026EPL (Europhysics Letters)Open Access

DiffGLE: Differentiable coarse-grained dynamics using generalized Langevin equation

View Full Paper
Ask AI
Bookmark
Share

Authors

JJJinu JeongINIshan Nadkarni

Discussion

Loading...

Member takes

Overview

Computational study demonstrates improved dynamical fidelity in molecular simulations, highlighting top-down learning of non-Markovian memory kernels.

Key Points

  • To develop a differentiable simulation framework that learns non-Markovian memory kernels for generalized Langevin equation closures without requiring explicit projected-force reconstruction.
  • Combined differentiable simulation with a trainable colored-noise filter to generate stationary random forces and define friction memory satisfying fluctuation-dissipation consistency.
  • Optimized memory parameters via end-to-end backpropagation through coarse-grained trajectories to match target velocity autocorrelation functions directly.
  • Tested performance on benchmark models including bulk water, bulk carbon dioxide, and a single-particle star polymer.
  • DiffGLE enhanced dynamical correlation agreement across bulk water, bulk carbon dioxide, and star-polymer benchmarks compared to standard coarse-grained methods.
  • The framework accurately reproduced non-Markovian dynamics while fully preserving the underlying conservative potential and structural equilibrium properties.

Cite This Study

Jeong et al. (2026) studied this question.

synapsesocial.com/papers/6a895e6bca7ade938187c80bhttps://doi.org/10.1209/0295-5075/ae9c6e
View Full Paper
Ask AI
Bookmark
Share