Speculative Sampling For Faster Molecular Dynamics
Arthur Kosmala, Stephan Günnemann, Meng Gao, Brandon M. Wood
ICML 2026 regular
Tóm tắt (nguồn: OpenReview · © tác giả)
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 **L**angevin **S**peculative **D**ynamics (**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.
Từ khoá
Metadata từ BioTender-max/icml2026-ai-bio (CC0-1.0). Phở không lưu trữ bản PDF; link trỏ về nguồn gốc.
Cùng chủ đề
Towards Sub-Second Molecular Docking as a Structural Primitive: A Quantized Consistency Diffusion Framework
Kexin Zhang, Weichen Qin, Yue Teng, Jiale Yu +4
Agent-centered scientific discovery is turning scientific models into always-on computational infrastructure. In this paradigm, AI agents coordinate tools, interpret feedback, and…
A Call to Lagrangian Action: Learning Population Mechanics from Temporal Snapshots
Vincent Guan, Lazar Atanackovic, Kirill Neklyudov
The population dynamics of molecules, cells, and organisms are governed by a number of unknown internal and external forces. In the last decade, population dynamics have…
DeCoDe: Decoupling Binding Position and Molecular Conformation in 3D Ligand Diffusion for Structure-Based Drug Design
Julong Yang, Wen Huang, Junhui Chen, Jian Peng
Recent advances in diffusion models show promise for Structure-Based Drug Design (SBDD), which aims to generate 3D ligand molecules that bind tightly to specific protein targets.…