Training models using forces computed by stochastic electronic structure methods

Abstract

Quantum Monte Carlo (QMC) can play a very important role in generating accurate data needed for constructing potential energy surfaces. We argue that QMC has advantages in terms of a smaller systematic bias and an ability to cover phase space more completely. The stochastic noise can ease the training of the machine learning model. We discuss how stochastic errors affect the generation of effective models by analyzing the errors within a linear least squares procedure, finding that there is an advantage to having many relatively imprecise data points for constructing models. We then analyze the effect of noise on a model of many-body silicon finding that noise in some situations improves the resulting model. We then study the effect of QMC noise on two machine learning models of dense hydrogen used in a recent study of its phase diagram. The noise enable us to estimate the errors in the model. We conclude with a discussion of future research problems.

References in corpus (27)

• Van der Waals Density Functional for General Geometries
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Visualizing the Loss Landscape of Neural Nets
• Twist-averaged Boundary Conditions in Continuum Quantum Monte Carlo
• QMCPACK : An open source ab initio Quantum Monte Carlo package for the electronic structure of atoms, molecules, and solids
• Deep Potential: a general representation of a many-body potential energy surface
• Towards the solution of the many-electron problem in real materials: equation of state of the hydrogen chain with state-of-the-art many-body methods
• The Finite Size Error in Many-body Simulations with long-Ranged Interactions
• Evidence for supercritical behavior of high-pressure liquid hydrogen
• QMCPACK: Advances in the development, efficiency, and application of auxiliary field and real-space variational and diffusion Quantum Monte Carlo
• Variational and Diffusion Quantum Monte Carlo Calculations with the CASINO Code
• Theory of Finite Size Effects for Electronic Quantum Monte Carlo Calculations of Liquids and Solids
• Backflow Correlations for the Electron Gas and Metallic Hydrogen
• Benchmark of Exchange-Correlation Functionals for High Pressure Hydrogen using Quantum Monte Carlo
• TurboRVB: a many-body toolkit for {\it ab initio} electronic simulations by quantum Monte Carlo
• Accurate, efficient and simple forces with Quantum Monte Carlo methods
• Wave function Ansatz (but Periodic) Networks and the Homogeneous Electron Gas
• Benchmarking Hydrogen-Helium Mixtures with QMC: Energetics, Pressures, and Forces
• Nonlinear Network description for many-body quantum systems in continuous space
• Stable solid molecular hydrogen above 900K from a machine-learned potential trained with diffusion Quantum Monte Carlo
• Trial wave functions for High-Pressure Metallic Hydrogen
• Ab-initio study of interacting fermions at finite temperature with neural canonical transformation
• Deep Variational Free Energy Approach to Dense Hydrogen
• Space-warp coordinate transformation for efficient ionic force calculations in quantum Monte Carlo
• The Path Integral Monte Carlo Calculation of Electronic Forces

Cited by in corpus (5)

• First principles simulations of dense hydrogen
• Accurate quantum Monte Carlo forces for machine-learned force fields: Ethanol as a benchmark
• Efficient calculation of unbiased atomic forces in ab initio Variational Monte Carlo
• Reproducibility of fixed-node diffusion Monte Carlo across diverse community codes: The case of water-methane dimer
• Fast Evaluation of Unbiased Atomic Forces in ab initio Variational Monte Carlo via the Lagrangian Technique