Speculative Sampling for Faster Molecular Dynamics

MCML Authors

Stephan Günnemann

Prof. Dr.

Core PI

Data Analytics & Machine Learning

Abstract

Molecular dynamics (MD) is a key tool for simulating the dynamical behavior of atomic systems. However, MD is inherently serial, which makes it difficult to increase single-system throughput with concurrent compute. To address this, we introduce Langevin Speculative Dynamics (LSD), a distributed and model-agnostic speculative sampler for accelerating MD without adding relative error. Inspired by speculative methods in language and diffusion modeling, LSD uses a draft model to propose fast simulation steps and verifies them in parallel with a slower target model, applying a transport map from the draft to the target distribution. We extend speculative sampling to second-order Langevin dynamics, derive the achievable speedup as a function of physical parameters, show that LSD generalizes across different systems and draft-target combinations with a 3-9x speedup, and confirm theoretically and empirically that LSD samples trajectories from the same distribution as its target model.

inproceedings KGG+26

---

ICML 2026

43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available.

---

Authors

A. Kosmala • S. Günnemann • M. Gao • B. M. Wood

---

Links

URL GitHub

---

Research Area

 A3 | Computational Models