Nonlinear gradient denoising: Finding accurate extrema from inaccurate functional derivatives
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Snyder, John C. | - |
dc.contributor.author | Rupp, Matthias | - |
dc.contributor.author | Mueller, Klaus-Robert | - |
dc.contributor.author | Burke, Kieron | - |
dc.date.accessioned | 2021-09-04T13:30:03Z | - |
dc.date.available | 2021-09-04T13:30:03Z | - |
dc.date.created | 2021-06-18 | - |
dc.date.issued | 2015-08-15 | - |
dc.identifier.issn | 0020-7608 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/92753 | - |
dc.description.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. (c) 2015 Wiley Periodicals, Inc. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | WILEY-BLACKWELL | - |
dc.subject | MACHINE | - |
dc.subject | ENERGY | - |
dc.title | Nonlinear gradient denoising: Finding accurate extrema from inaccurate functional derivatives | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Mueller, Klaus-Robert | - |
dc.identifier.doi | 10.1002/qua.24937 | - |
dc.identifier.scopusid | 2-s2.0-84936751541 | - |
dc.identifier.wosid | 000357606000011 | - |
dc.identifier.bibliographicCitation | INTERNATIONAL JOURNAL OF QUANTUM CHEMISTRY, v.115, no.16, pp.1102 - 1114 | - |
dc.relation.isPartOf | INTERNATIONAL JOURNAL OF QUANTUM CHEMISTRY | - |
dc.citation.title | INTERNATIONAL JOURNAL OF QUANTUM CHEMISTRY | - |
dc.citation.volume | 115 | - |
dc.citation.number | 16 | - |
dc.citation.startPage | 1102 | - |
dc.citation.endPage | 1114 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Chemistry | - |
dc.relation.journalResearchArea | Mathematics | - |
dc.relation.journalResearchArea | Physics | - |
dc.relation.journalWebOfScienceCategory | Chemistry, Physical | - |
dc.relation.journalWebOfScienceCategory | Mathematics, Interdisciplinary Applications | - |
dc.relation.journalWebOfScienceCategory | Quantum Science & Technology | - |
dc.relation.journalWebOfScienceCategory | Physics, Atomic, Molecular & Chemical | - |
dc.subject.keywordPlus | MACHINE | - |
dc.subject.keywordPlus | ENERGY | - |
dc.subject.keywordAuthor | density functional theory | - |
dc.subject.keywordAuthor | machine learning | - |
dc.subject.keywordAuthor | nonlinear gradient denoising | - |
dc.subject.keywordAuthor | orbital-free density functional theory | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
145 Anam-ro, Seongbuk-gu, Seoul, 02841, Korea+82-2-3290-2963
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.