Nikbakht Silab, RasoulJonsson, Anders, 1973-Lozano Solsona, Angel2021-05-132021-05-132021Nikbakht R, Jonsson A, Lozano A. Unsupervised learning for parametric optimization. IEEE Commun Lett. 2021;25(3):678-81. DOI: 10.1109/LCOMM.2020.30279811089-7798http://hdl.handle.net/10230/47546This 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.application/pdfeng© 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.2020.3027981info:eu-repo/semantics/articlehttp://dx.doi.org/10.1109/LCOMM.2020.3027981Machine learningNeural networksUnsupervised learningParametric optimizationConvex optimizationQuadratic programinfo:eu-repo/semantics/openAccess