Finding Density Functionals with Machine Learning

Snyder, John C.; Rupp, Matthias; Hansen, Katja; Müller, Klaus-Robert; Burke, Kieron

Finding Density Functionals with Machine Learning

Dateien

Zu diesem Dokument gibt es keine Dateien.

Datum

2012

Autor:innen

Snyder, John C.

Rupp, Matthias

Hansen, Katja

Müller, Klaus-Robert

Burke, Kieron

Publikationstyp

Zeitschriftenartikel

Publikationsstatus

Published

Erschienen in

Physical Review Letters. American Physical Society (APS). 2012, 108(25), 253002. ISSN 0031-9007. eISSN 1079-7114. Available under: doi: 10.1103/PhysRevLett.108.253002

Zusammenfassung

Machine learning is used to approximate density functionals. For the model problem of the kinetic energy of noninteracting fermions in 1D, mean absolute errors below 1 kcal/mol on test densities similar to the training set are reached with fewer than 100 training densities. A predictor identifies if a test density is within the interpolation region. Via principal component analysis, a projected functional derivative finds highly accurate self-consistent densities. The challenges for application of our method to real electronic structure problems are discussed.

Fachgebiet (DDC)

004 Informatik

Zitieren

ISO 690

SNYDER, John C., Matthias RUPP, Katja HANSEN, Klaus-Robert MÜLLER, Kieron BURKE, 2012. Finding Density Functionals with Machine Learning. In: Physical Review Letters. American Physical Society (APS). 2012, 108(25), 253002. ISSN 0031-9007. eISSN 1079-7114. Available under: doi: 10.1103/PhysRevLett.108.253002

BibTex

@article{Snyder2012-06-22Findi-52164,
  year={2012},
  doi={10.1103/PhysRevLett.108.253002},
  title={Finding Density Functionals with Machine Learning},
  number={25},
  volume={108},
  issn={0031-9007},
  journal={Physical Review Letters},
  author={Snyder, John C. and Rupp, Matthias and Hansen, Katja and Müller, Klaus-Robert and Burke, Kieron},
  note={Article Number: 253002}
}

RDF

<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/52164">
    <dc:creator>Hansen, Katja</dc:creator>
    <dc:creator>Müller, Klaus-Robert</dc:creator>
    <dc:contributor>Snyder, John C.</dc:contributor>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:language>eng</dc:language>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:contributor>Müller, Klaus-Robert</dc:contributor>
    <dc:contributor>Burke, Kieron</dc:contributor>
    <dcterms:title>Finding Density Functionals with Machine Learning</dcterms:title>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-12-17T14:29:21Z</dc:date>
    <dc:creator>Snyder, John C.</dc:creator>
    <dcterms:issued>2012-06-22</dcterms:issued>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-12-17T14:29:21Z</dcterms:available>
    <dc:creator>Rupp, Matthias</dc:creator>
    <dcterms:abstract xml:lang="eng">Machine learning is used to approximate density functionals. For the model problem of the kinetic energy of noninteracting fermions in 1D, mean absolute errors below 1  kcal/mol on test densities similar to the training set are reached with fewer than 100 training densities. A predictor identifies if a test density is within the interpolation region. Via principal component analysis, a projected functional derivative finds highly accurate self-consistent densities. The challenges for application of our method to real electronic structure problems are discussed.</dcterms:abstract>
    <dc:contributor>Hansen, Katja</dc:contributor>
    <dc:creator>Burke, Kieron</dc:creator>
    <dc:rights>terms-of-use</dc:rights>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Rupp, Matthias</dc:contributor>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/52164"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Nein

Begutachtet

Ja