Neural Thermodynamic Integration: Free Energies from Energy-based Diffusion Models
- URL: http://arxiv.org/abs/2406.02313v2
- Date: Wed, 12 Jun 2024 16:08:29 GMT
- Title: Neural Thermodynamic Integration: Free Energies from Energy-based Diffusion Models
- Authors: Bálint Máté, François Fleuret, Tristan Bereau,
- Abstract summary: Thermodynamic integration (TI) offers a rigorous method for estimating free-energy differences.
We propose to perform TI along an alchemical pathway represented by a trainable neural network, which we term Neural TI.
The ability of the resulting energy-based diffusion model to sample all intermediate ensembles allows us to perform TI from a single reference calculation.
- Score: 19.871787625519513
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Thermodynamic integration (TI) offers a rigorous method for estimating free-energy differences by integrating over a sequence of interpolating conformational ensembles. However, TI calculations are computationally expensive and typically limited to coupling a small number of degrees of freedom due to the need to sample numerous intermediate ensembles with sufficient conformational-space overlap. In this work, we propose to perform TI along an alchemical pathway represented by a trainable neural network, which we term Neural TI. Critically, we parametrize a time-dependent Hamiltonian interpolating between the interacting and non-interacting systems, and optimize its gradient using a denoising-diffusion objective. The ability of the resulting energy-based diffusion model to sample all intermediate ensembles allows us to perform TI from a single reference calculation. We apply our method to Lennard-Jones fluids, where we report accurate calculations of the excess chemical potential, demonstrating that Neural TI is capable of coupling hundreds of degrees of freedom at once.
Related papers
- Dynamical Measure Transport and Neural PDE Solvers for Sampling [77.38204731939273]
We tackle the task of sampling from a probability density as transporting a tractable density function to the target.
We employ physics-informed neural networks (PINNs) to approximate the respective partial differential equations (PDEs) solutions.
PINNs allow for simulation- and discretization-free optimization and can be trained very efficiently.
arXiv Detail & Related papers (2024-07-10T17:39:50Z) - D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theory [79.50644650795012]
We propose a deep learning approach to solve Kohn-Sham Density Functional Theory (KS-DFT)
We prove that such an approach has the same expressivity as the SCF method, yet reduces the computational complexity.
In addition, we show that our approach enables us to explore more complex neural-based wave functions.
arXiv Detail & Related papers (2023-03-01T10:38:10Z) - Sampling with Mollified Interaction Energy Descent [57.00583139477843]
We present a new optimization-based method for sampling called mollified interaction energy descent (MIED)
MIED minimizes a new class of energies on probability measures called mollified interaction energies (MIEs)
We show experimentally that for unconstrained sampling problems our algorithm performs on par with existing particle-based algorithms like SVGD.
arXiv Detail & Related papers (2022-10-24T16:54:18Z) - Physics-constrained Unsupervised Learning of Partial Differential
Equations using Meshes [1.066048003460524]
Graph neural networks show promise in accurately representing irregularly meshed objects and learning their dynamics.
In this work, we represent meshes naturally as graphs, process these using Graph Networks, and formulate our physics-based loss to provide an unsupervised learning framework for partial differential equations (PDE)
Our framework will enable the application of PDE solvers in interactive settings, such as model-based control of soft-body deformations.
arXiv Detail & Related papers (2022-03-30T19:22:56Z) - A2I Transformer: Permutation-equivariant attention network for pairwise
and many-body interactions with minimal featurization [0.1469945565246172]
In this work, we suggest an end-to-end model which directly predicts per-atom energy from the coordinates of particles.
We tested our model against several challenges in molecular simulation problems, including periodic boundary condition (PBC), $n$-body interaction, and binary composition.
arXiv Detail & Related papers (2021-10-27T12:18:25Z) - Dual Training of Energy-Based Models with Overparametrized Shallow
Neural Networks [41.702175127106784]
Energy-based models (EBMs) are generative models that are usually trained via maximum likelihood estimation.
We propose a dual formulation of an EBMs algorithm in which the particles are sometimes restarted at random samples drawn from the data set, and show that performing these restarts corresponds to a score every step.
These results are illustrated in simple numerical experiments.
arXiv Detail & Related papers (2021-07-11T21:43:18Z) - Accelerating Finite-temperature Kohn-Sham Density Functional Theory with
Deep Neural Networks [2.7035666571881856]
We present a numerical modeling workflow based on machine learning (ML) which reproduces the the total energies produced by Kohn-Sham density functional theory (DFT) at finite electronic temperature.
Based on deep neural networks, our workflow yields the local density of states (LDOS) for a given atomic configuration.
We demonstrate the efficacy of this approach for both solid and liquid metals and compare results between independent and unified machine-learning models for solid and liquid aluminum.
arXiv Detail & Related papers (2020-10-10T05:38:03Z) - Multipole Graph Neural Operator for Parametric Partial Differential
Equations [57.90284928158383]
One of the main challenges in using deep learning-based methods for simulating physical systems is formulating physics-based data.
We propose a novel multi-level graph neural network framework that captures interaction at all ranges with only linear complexity.
Experiments confirm our multi-graph network learns discretization-invariant solution operators to PDEs and can be evaluated in linear time.
arXiv Detail & Related papers (2020-06-16T21:56:22Z) - Method of spectral Green functions in driven open quantum dynamics [77.34726150561087]
A novel method based on spectral Green functions is presented for the simulation of driven open quantum dynamics.
The formalism shows remarkable analogies to the use of Green functions in quantum field theory.
The method dramatically reduces computational cost compared with simulations based on solving the full master equation.
arXiv Detail & Related papers (2020-06-04T09:41:08Z) - A Near-Optimal Gradient Flow for Learning Neural Energy-Based Models [93.24030378630175]
We propose a novel numerical scheme to optimize the gradient flows for learning energy-based models (EBMs)
We derive a second-order Wasserstein gradient flow of the global relative entropy from Fokker-Planck equation.
Compared with existing schemes, Wasserstein gradient flow is a smoother and near-optimal numerical scheme to approximate real data densities.
arXiv Detail & Related papers (2019-10-31T02:26:20Z)
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.