Solving deep-learning density functional theory via variational autoencoders
arXiv:2403.09788 · doi:10.1088/2632-2153/ad611f
Abstract
In recent years, machine learning models, chiefly deep neural networks, have revealed suited to learn accurate energy-density functionals from data. However, problematic instabilities have been shown to occur in the search of ground-state density profiles via energy minimization. Indeed, any small noise can lead astray from realistic profiles, causing the failure of the learned functional and, hence, strong violations of the variational property. In this article, we employ variational autoencoders to build a compressed, flexible, and regular representation of the ground-state density profiles of various quantum models. Performing energy minimization in this compressed space allows us to avoid both numerical instabilities and variational biases due to excessive constraints. Our tests are performed on one-dimensional single-particle models from the literature in the field and, notably, on a three-dimensional disordered potential. In all cases, the ground-state energies are estimated with errors below the chemical accuracy and the density profiles are accurately reproduced without numerical artifacts.
11 pages, 8 figures
References in corpus (14)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Deep-Learning Density Functional Theory Hamiltonian for Efficient ab initio Electronic-Structure Calculation
- Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physics
- Pure density functional for strong correlations and the thermodynamic limit from machine learning
- Toward Orbital-Free Density Functional Theory with Small Data Sets and Deep Learning
- Overcoming the Barrier of Orbital-Free Density Functional Theory for Molecular Systems Using Deep Learning
- Automatic Differentiation for the Direct Minimization Approach to the Hartree-Fock Method
- Automatic Differentiation for Orbital-Free Density Functional Theory
- Variational principle to regularize machine-learned density functionals: the non-interacting kinetic-energy functional
- Localization of interacting Fermi gases in quasiperiodic potentials
- Machine-learning Kohn-Sham potential from dynamics in time-dependent Kohn-Sham systems
- Deep learning density functionals for gradient descent optimization
- Deep learning nonlocal and scalable energy functionals for quantum Ising models
- Orbital-Free Density Functional Theory with Continuous Normalizing Flows