Molecular relaxation by reverse diffusion with time step prediction
- URL: http://arxiv.org/abs/2404.10935v1
- Date: Tue, 16 Apr 2024 22:15:52 GMT
- Title: Molecular relaxation by reverse diffusion with time step prediction
- Authors: Khaled Kahouli, Stefaan Simon Pierre Hessmann, Klaus-Robert Müller, Shinichi Nakajima, Stefan Gugler, Niklas Wolf Andreas Gebauer,
- Abstract summary: MoreRed is a conceptually novel and purely statistical approach to finding the equilibrium state of a non-equilibrium structure.
It is trained on a significantly smaller, and thus computationally cheaper, dataset consisting of solely unlabeled equilibrium structures.
We compare MoreRed to classical force fields, equivariant neural network force fields trained on a large dataset of equilibrium and non-equilibrium data, as well as a semi-empirical tight-binding model.
- Score: 13.834005606387706
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Molecular relaxation, finding the equilibrium state of a non-equilibrium structure, is an essential component of computational chemistry to understand reactivity. Classical force field methods often rely on insufficient local energy minimization, while neural network force field models require large labeled datasets encompassing both equilibrium and non-equilibrium structures. As a remedy, we propose MoreRed, molecular relaxation by reverse diffusion, a conceptually novel and purely statistical approach where non-equilibrium structures are treated as noisy instances of their corresponding equilibrium states. To enable the denoising of arbitrarily noisy inputs via a generative diffusion model, we further introduce a novel diffusion time step predictor. Notably, MoreRed learns a simpler pseudo potential energy surface instead of the complex physical potential energy surface. It is trained on a significantly smaller, and thus computationally cheaper, dataset consisting of solely unlabeled equilibrium structures, avoiding the computation of non-equilibrium structures altogether. We compare MoreRed to classical force fields, equivariant neural network force fields trained on a large dataset of equilibrium and non-equilibrium data, as well as a semi-empirical tight-binding model. To assess this quantitatively, we evaluate the root-mean-square deviation between the found equilibrium structures and the reference equilibrium structures as well as their DFT energies.
Related papers
- Out-of-equilibrium Eigenstate Thermalization Hypothesis [0.0]
We show that universality, exponentially small cross-correlations between the observable and the initial state matrix elements determine relaxation dynamics toward equilibrium.
We numerically verify scaling and cross-correlation, point out the emergent of the high-frequency behavior, and outline possible generalizations.
arXiv Detail & Related papers (2024-06-07T06:54:14Z) - Neural force functional for non-equilibrium many-body colloidal systems [0.20971479389679337]
We combine power functional theory and machine learning to study non-equilibrium overdamped many-body systems of colloidal particles.
We first sample in steady state the one-body fields relevant for the dynamics from computer simulations of Brownian particles.
A neural network is then trained with this data to represent locally in space the formally exact functional mapping from the one-body density and velocity profiles to the one-body internal force field.
arXiv Detail & Related papers (2024-06-05T19:57:23Z) - Improving equilibrium propagation without weight symmetry through Jacobian homeostasis [7.573586022424398]
Equilibrium propagation (EP) is a compelling alternative to the backpropagation of error algorithm (BP)
EP requires weight symmetry and infinitesimal equilibrium perturbations, i.e., nudges, to estimate unbiased gradients efficiently.
We show that the finite nudge does not pose a problem, as exact derivatives can still be estimated via a Cauchy integral.
We present a new homeostatic objective that directly mitigates functional asymmetries of the Jacobian at the network's fixed point.
arXiv Detail & Related papers (2023-09-05T13:20:43Z) - May the Force be with You: Unified Force-Centric Pre-Training for 3D
Molecular Conformations [19.273404278711794]
We propose a force-centric pretraining model for 3D molecular conformations covering both equilibrium and off-equilibrium data.
For equilibrium data, we introduce zero-force regularization and forced-based denoising techniques to approximate near-equilibrium forces.
Experiments show that, with our pre-training objective, we increase forces accuracy by around 3 times compared to the un-pre-trained Equivariant Transformer model.
arXiv Detail & Related papers (2023-08-24T01:54:02Z) - Towards Predicting Equilibrium Distributions for Molecular Systems with
Deep Learning [60.02391969049972]
We introduce a novel deep learning framework, called Distributional Graphormer (DiG), in an attempt to predict the equilibrium distribution of molecular systems.
DiG employs deep neural networks to transform a simple distribution towards the equilibrium distribution, conditioned on a descriptor of a molecular system.
arXiv Detail & Related papers (2023-06-08T17:12:08Z) - Machine learning in and out of equilibrium [58.88325379746631]
Our study uses a Fokker-Planck approach, adapted from statistical physics, to explore these parallels.
We focus in particular on the stationary state of the system in the long-time limit, which in conventional SGD is out of equilibrium.
We propose a new variation of Langevin dynamics (SGLD) that harnesses without replacement minibatching.
arXiv Detail & Related papers (2023-06-06T09:12:49Z) - Simulating scalar field theories on quantum computers with limited
resources [62.997667081978825]
We present a quantum algorithm for implementing $phi4$ lattice scalar field theory on qubit computers.
The algorithm allows efficient $phi4$ state preparation for a large range of input parameters in both the normal and broken symmetry phases.
arXiv Detail & Related papers (2022-10-14T17:28:15Z) - Global Convergence of Over-parameterized Deep Equilibrium Models [52.65330015267245]
A deep equilibrium model (DEQ) is implicitly defined through an equilibrium point of an infinite-depth weight-tied model with an input-injection.
Instead of infinite computations, it solves an equilibrium point directly with root-finding and computes gradients with implicit differentiation.
We propose a novel probabilistic framework to overcome the technical difficulty in the non-asymptotic analysis of infinite-depth weight-tied models.
arXiv Detail & Related papers (2022-05-27T08:00:13Z) - Spherical Motion Dynamics: Learning Dynamics of Neural Network with
Normalization, Weight Decay, and SGD [105.99301967452334]
We show the learning dynamics of neural network with normalization, weight decay (WD), and SGD (with momentum) named as Spherical Motion Dynamics (SMD)
We verify our assumptions and theoretical results on various computer vision tasks including ImageNet and MSCOCO with standard settings.
arXiv Detail & Related papers (2020-06-15T14:16:33Z) - Multiplicative noise and heavy tails in stochastic optimization [62.993432503309485]
empirical optimization is central to modern machine learning, but its role in its success is still unclear.
We show that it commonly arises in parameters of discrete multiplicative noise due to variance.
A detailed analysis is conducted in which we describe on key factors, including recent step size, and data, all exhibit similar results on state-of-the-art neural network models.
arXiv Detail & Related papers (2020-06-11T09:58:01Z)
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.