GPU-accelerated approximate kernel method for quantum machine learning-Reference-Cited by-同舟云学术

GPU-accelerated approximate kernel method for quantum machine learning

Published:2022-12-07 Issue:21 Volume:157 Page:214801
ISSN:0021-9606
Container-title:The Journal of Chemical Physics
language:en
Short-container-title:J. Chem. Phys.

Author:

Browning Nicholas J.¹^ORCID,Faber Felix A.²^ORCID,Anatole von Lilienfeld O.³⁴^ORCID

Affiliation:

1. Institute of Physical Chemistry and National Center for Computational Design and Discovery of Novel Materials, Department of Chemistry, University of Basel, Klingelbergstrasse 80, CH-4056 Basel, Switzerland

2. Department of Physics, University of Cambridge, Cambridge, United Kingdom

3. Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany

4. Berlin Institute for the Foundations of Learning and Data, 10587 Berlin, Germany

Abstract

We introduce Quantum Machine Learning (QML)-Lightning, a PyTorch package containing graphics processing unit (GPU)-accelerated approximate kernel models, which can yield trained models within seconds. QML-Lightning includes a cost-efficient GPU implementation of FCHL19, which together can provide energy and force predictions with competitive accuracy on a microsecond per atom timescale. Using modern GPU hardware, we report learning curves of energies and forces as well as timings as numerical evidence for select legacy benchmarks from atomistic simulation including QM9, MD-17, and 3BPA.

Funder

National Center of Competence in Research Materials' Revolution: Computational Design and Discovery of Novel Materials

Publisher

AIP Publishing

Subject

Physical and Theoretical Chemistry,General Physics and Astronomy

Link

https://aip.scitation.org/doi/pdf/10.1063/5.0108967

Reference63 articles.

1. Ab Initio Machine Learning in Chemical Compound Space

2. Retrospective on a decade of machine learning for chemical discovery

3. Machine learning meets chemical physics