Unsupervised learning for parametric optimization

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Nikbakht Silab, Rasoul
• dc.contributor.author Jonsson, Anders, 1973-
• dc.contributor.author Lozano Solsona, Angel
• dc.date.accessioned 2021-05-13T09:14:21Z
• dc.date.available 2021-05-13T09:14:21Z
• dc.date.issued 2021
• dc.description.abstract This letter proposes the unsupervised training of a feedforward neural network to solve parametric optimization problems involving large numbers of parameters. Such unsupervised training, which consists in repeatedly sampling parameter values and performing stochastic gradient descent, foregoes the taxing precomputation of labeled training data that supervised learning necessitates. As an example of application, we put this technique to use on a rather general constrained quadratic program. Follow-up letters subsequently apply it to more specialized wireless communication problems, some of them nonconvex in nature. In all cases, the performance of the proposed procedure is very satisfactory and, in terms of computational cost, its scalability with the problem dimensionality is superior to that of convex solvers.
• dc.description.sponsorship This work was supported by the European Research Council under the H2020 Framework Programme/ERC grant agreement 694974, by the Maria de Maeztu Units of Excellence Programme (MDM-2015-0502) as well as by MINECO’s Projects RTI2018-102112 and RTI2018-101040, and by the ICREA Academia program.
• dc.format.mimetype application/pdf
• dc.identifier.citation Nikbakht R, Jonsson A, Lozano A. Unsupervised learning for parametric optimization. IEEE Commun Lett. 2021;25(3):678-81. DOI: 10.1109/LCOMM.2020.3027981
• dc.identifier.doi http://dx.doi.org/10.1109/LCOMM.2020.3027981
• dc.identifier.issn 1089-7798
• dc.identifier.uri http://hdl.handle.net/10230/47546
• dc.language.iso eng
• dc.publisher Institute of Electrical and Electronics Engineers (IEEE)
• dc.relation.ispartof IEEE Communications Letters. 2021;25(3):678-81
• dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/694974
• dc.relation.projectID info:eu-repo/grantAgreement/ES/2PE/RTI2018-102112
• dc.relation.projectID info:eu-repo/grantAgreement/ES/2PE/RTI2018-101040
• dc.rights © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. http://dx.doi.org/10.1109/LCOMM.2020.3027981
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.subject.keyword Machine learning
• dc.subject.keyword Neural networks
• dc.subject.keyword Unsupervised learning
• dc.subject.keyword Parametric optimization
• dc.subject.keyword Convex optimization
• dc.subject.keyword Quadratic program
• dc.title Unsupervised learning for parametric optimization
• dc.type info:eu-repo/semantics/article
• dc.type.version info:eu-repo/semantics/acceptedVersion