Saved in:
Bibliographic Details
Main Authors: Ceperley, David M., Jensen, Scott, Yang, Yubo, Niu, Hongwei, Pierleoni, Carlo, Holzmann, Markus
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2310.15994
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916230278938624
author Ceperley, David M.
Jensen, Scott
Yang, Yubo
Niu, Hongwei
Pierleoni, Carlo
Holzmann, Markus
author_facet Ceperley, David M.
Jensen, Scott
Yang, Yubo
Niu, Hongwei
Pierleoni, Carlo
Holzmann, Markus
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2310_15994
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Training models using forces computed by stochastic electronic structure methods
Ceperley, David M.
Jensen, Scott
Yang, Yubo
Niu, Hongwei
Pierleoni, Carlo
Holzmann, Markus
Materials Science
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.
title Training models using forces computed by stochastic electronic structure methods
topic Materials Science
url https://arxiv.org/abs/2310.15994