Nonlinear gradient denoising : Finding accurate extrema from inaccurate functional derivatives
Nonlinear gradient denoising : Finding accurate extrema from inaccurate functional derivatives
No Thumbnail Available
Files
There are no files associated with this item.
Date
2015
Authors
Editors
Journal ISSN
Electronic ISSN
ISBN
Bibliographical data
Publisher
Series
DOI (citable link)
International patent number
Link to the license
EU project number
Project
Open Access publication
Collections
Title in another language
Publication type
Journal article
Publication status
Published
Published in
International Journal of Quantum Chemistry ; 115 (2015), 16. - pp. 1102-1114. - Wiley-Blackwell. - ISSN 0020-7608. - eISSN 1097-461X
Abstract
A method for nonlinear optimization with machine learning (ML) models, called nonlinear gradient denoising (NLGD), is developed, and applied with ML approximations to the kinetic energy density functional in an orbital‐free density functional theory. Due to systematically inaccurate gradients of ML models, in particular when the data is very high‐dimensional, the optimization must be constrained to the data manifold. We use nonlinear kernel principal component analysis (PCA) to locally reconstruct the manifold, enabling a projected gradient descent along it. A thorough analysis of the method is given via a simple model, designed to clarify the concepts presented. Additionally, NLGD is compared with the local PCA method used in previous work. Our method is shown to be superior in cases when the data manifold is highly nonlinear and high dimensional. Further applications of the method in both density functional theory and ML are discussed.
Summary in another language
Subject (DDC)
004 Computer Science
Keywords
density functional theory, machine learning, nonlinear gradient denoising, orbital‐free density functional theory
Conference
Review
undefined / . - undefined, undefined. - (undefined; undefined)
Cite This
ISO 690
SNYDER, John C., Matthias RUPP, Klaus-Robert MÜLLER, Kieron BURKE, 2015. Nonlinear gradient denoising : Finding accurate extrema from inaccurate functional derivatives. In: International Journal of Quantum Chemistry. Wiley-Blackwell. 115(16), pp. 1102-1114. ISSN 0020-7608. eISSN 1097-461X. Available under: doi: 10.1002/qua.24937BibTex
@article{Snyder2015Nonli-52135, year={2015}, doi={10.1002/qua.24937}, title={Nonlinear gradient denoising : Finding accurate extrema from inaccurate functional derivatives}, number={16}, volume={115}, issn={0020-7608}, journal={International Journal of Quantum Chemistry}, pages={1102--1114}, author={Snyder, John C. and Rupp, Matthias and Müller, Klaus-Robert and Burke, Kieron} }
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/123456789/52135"> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-12-15T13:15:48Z</dc:date> <dc:rights>terms-of-use</dc:rights> <dc:creator>Rupp, Matthias</dc:creator> <dc:contributor>Burke, Kieron</dc:contributor> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/> <foaf:homepage rdf:resource="http://localhost:8080/"/> <dc:creator>Müller, Klaus-Robert</dc:creator> <dcterms:issued>2015</dcterms:issued> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/52135"/> <dc:creator>Snyder, John C.</dc:creator> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-12-15T13:15:48Z</dcterms:available> <dc:contributor>Snyder, John C.</dc:contributor> <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/> <dc:creator>Burke, Kieron</dc:creator> <dc:contributor>Rupp, Matthias</dc:contributor> <dc:contributor>Müller, Klaus-Robert</dc:contributor> <dc:language>eng</dc:language> <dcterms:abstract xml:lang="eng">A method for nonlinear optimization with machine learning (ML) models, called nonlinear gradient denoising (NLGD), is developed, and applied with ML approximations to the kinetic energy density functional in an orbital‐free density functional theory. Due to systematically inaccurate gradients of ML models, in particular when the data is very high‐dimensional, the optimization must be constrained to the data manifold. We use nonlinear kernel principal component analysis (PCA) to locally reconstruct the manifold, enabling a projected gradient descent along it. A thorough analysis of the method is given via a simple model, designed to clarify the concepts presented. Additionally, NLGD is compared with the local PCA method used in previous work. Our method is shown to be superior in cases when the data manifold is highly nonlinear and high dimensional. Further applications of the method in both density functional theory and ML are discussed.</dcterms:abstract> <dcterms:title>Nonlinear gradient denoising : Finding accurate extrema from inaccurate functional derivatives</dcterms:title> </rdf:Description> </rdf:RDF>
Internal note
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Examination date of dissertation
Method of financing
Comment on publication
Alliance license
Corresponding Authors der Uni Konstanz vorhanden
International Co-Authors
Bibliography of Konstanz
No
Refereed
Unknown