Hessian Matching for Machine-Learned Coarse-Grained Molecular Dynamics

• URL: http://arxiv.org/abs/2605.12823v1
• Date: Tue, 12 May 2026 23:46:38 GMT
• Title: Hessian Matching for Machine-Learned Coarse-Grained Molecular Dynamics
• Abstract summary: We introduce a framework that augments force matching with Hessian-vector product (HVP) matching, instilling second-order curvature information into CG potentials without constructing the full Hessian.<n>Our results demonstrate that higher-order physical supervision is a practical path to more accurate and transferable CG potentials for biomolecular simulation.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Coarse-grained (CG) molecular dynamics enables simulations of atomic systems such as biomolecules at timescales inaccessible to all-atom (AA) methods, but existing CG neural potentials trained via force matching capture only the gradient of the free-energy surface, leaving its curvature unconstrained. We introduce a framework that augments force matching with stochastic Hessian-vector product (HVP) matching, instilling second-order curvature information into CG potentials without constructing the full Hessian. We derive a decomposition of the target CG Hessian into a model-independent projected AA Hessian, precomputed once before training, and a model-dependent covariance correction computed online at negligible cost. We construct an unbiased stochastic estimator of the Hessian-matching objective by using random probe vectors. We evaluate our method by comparing against force matching on a benchmark of nine fast-folding proteins unseen during training. HVP matching outperforms plain force matching on 8 of 9 proteins on slow-mode metrics, with reductions of up to 85% in the Kullback--Leibler divergence between the CG and reference distributions along the slowest collective mode of the largest protein. Our results demonstrate that higher-order physical supervision is a practical path to more accurate and transferable CG potentials for biomolecular simulation.

Related papers

• Projected Hessian Learning: Fast Curvature Supervision for Accurate Machine-Learning Interatomic Potentials [3.0325110391148264]
  Projected Hessian Learning (PHL) is a scalable second-order training framework that injects curvature information using only Hessian-vector products (HVPs)<n>We benchmark PHL on a chemically diverse dataset of reactants, products transition states, and normal-mode sampled geometries computed at omegaB97XD/6-31G(d)<n>With randomized probes per minibatch, both HVP schemes match full-Hessian training in energy, force, and Hessian accuracy while delivering >24x speedups for the small molecular systems studied.
  arXiv  Detail & Related papers  (2026-03-04T19:09:16Z)
• Operator Forces For Coarse-Grained Molecular Dynamics [44.1462357579624]
  Machine-learned coarse-graining (MLCG) has emerged as a promising approach to construct highly accurate force fields for CG molecular dynamics.<n>We show that flow-based kernels can generate high-quality CG forces solely from configurational samples.
  arXiv  Detail & Related papers  (2025-06-24T13:51:20Z)
• Energy-Based Coarse-Graining in Molecular Dynamics: A Flow-Based Framework without Data [0.0]
  Coarse-grained (CG) models provide an effective route to reducing the complexity of molecular simulations.<n>We introduce a fully data-free, generative framework for CG that directly targets the all-atom Boltzmann distribution.<n>We show that the method captures all relevant modes of the Boltzmann distribution, reconstructs atomic configurations, and automatically learns physically meaningful CG representations.
  arXiv  Detail & Related papers  (2025-04-29T17:05:27Z)
• Rao-Blackwell Gradient Estimators for Equivariant Denoising Diffusion [55.95767828747407]
  In domains such as molecular and protein generation, physical systems exhibit inherent symmetries that are critical to model.<n>We present a framework that reduces training variance and provides a provably lower-variance gradient estimator.<n>We also present a practical implementation of this estimator incorporating the loss and sampling procedure through a method we call Orbit Diffusion.
  arXiv  Detail & Related papers  (2025-02-14T03:26:57Z)
• Statistically Optimal Force Aggregation for Coarse-Graining Molecular Dynamics [55.41644538483948]
  coarse-grained (CG) models have the potential to simulate large molecular complexes beyond what is possible with atomistic molecular dynamics. A widely used methodology for learning CG force-fields maps forces from all-atom molecular dynamics to the CG representation and matches them with a CG force-field on average. We show that there is flexibility in how to map all-atom forces to the CG representation, and that the most commonly used mapping methods are statistically inefficient and potentially even incorrect in the presence of constraints in the all-atom simulation.
  arXiv  Detail & Related papers  (2023-02-14T14:35:39Z)
• Two for One: Diffusion Models and Force Fields for Coarse-Grained Molecular Dynamics [15.660348943139711]
  We leverage connections between score-based generative models, force fields and molecular dynamics to learn a CG force field without requiring any force inputs during training. While having a vastly simplified training setup compared to previous work, we demonstrate that our approach leads to improved performance across several small- to medium-sized protein simulations.
  arXiv  Detail & Related papers  (2023-02-01T17:09:46Z)
• NAG-GS: Semi-Implicit, Accelerated and Robust Stochastic Optimizer [45.47667026025716]
  We propose a novel, robust and accelerated iteration that relies on two key elements. The convergence and stability of the obtained method, referred to as NAG-GS, are first studied extensively. We show that NAG-arity is competitive with state-the-art methods such as momentum SGD with weight decay and AdamW for the training of machine learning models.
  arXiv  Detail & Related papers  (2022-09-29T16:54:53Z)
• Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality [65.67315418971688]
  Nearest Orthogonal Gradient (NOG) and Optimal Learning Rate (OLR) are proposed. Experiments on visual recognition demonstrate that our methods can simultaneously improve the covariance conditioning and generalization.
  arXiv  Detail & Related papers  (2022-07-05T15:39:29Z)
• A Stochastic Newton Algorithm for Distributed Convex Optimization [62.20732134991661]
  We analyze a Newton algorithm for homogeneous distributed convex optimization, where each machine can calculate gradients of the same population objective. We show that our method can reduce the number, and frequency, of required communication rounds compared to existing methods without hurting performance.
  arXiv  Detail & Related papers  (2021-10-07T17:51:10Z)
• Fast Gravitational Approach for Rigid Point Set Registration with Ordinary Differential Equations [79.71184760864507]
  This article introduces a new physics-based method for rigid point set alignment called Fast Gravitational Approach (FGA) In FGA, the source and target point sets are interpreted as rigid particle swarms with masses interacting in a globally multiply-linked manner while moving in a simulated gravitational force field. We show that the new method class has characteristics not found in previous alignment methods.
  arXiv  Detail & Related papers  (2020-09-28T15:05:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.