Publicación:
Efficient projection onto the ? ?,1 mixed-norm ball using a newton root search method

dc.contributor.author Chau G. es_PE
dc.contributor.author Wohlberg B. es_PE
dc.contributor.author Rodriguez P. es_PE
dc.date.accessioned 2024-05-30T23:13:38Z
dc.date.available 2024-05-30T23:13:38Z
dc.date.issued 2019
dc.description.abstract Mixed norms that promote structured sparsity have numerous applications in signal processing and machine learning problems. In this work, we present a new algorithm, based on a Newton root search technique, for computing the projection onto the l ?,1 ball, which has found application in cognitive neuroscience and classification tasks. Numerical simulations show that our proposed method is between 8 and 10 times faster on average, and up to 20 times faster for very sparse solutions, than the previous state of the art. Tests on real functional magnetic resonance image data show that, for some data distributions, our algorithm can obtain speed improvements by a factor of between 10 and 100, depending on the implementation. © 2019 Society for Industrial and Applied Mathematics.
dc.description.sponsorship Consejo Nacional de Ciencia, Tecnología e Innovación Tecnológica - Concytec
dc.identifier.doi https://doi.org/10.1137/18M1212525
dc.identifier.scopus 2-s2.0-85064230441
dc.identifier.uri https://hdl.handle.net/20.500.12390/2741
dc.language.iso eng
dc.publisher Society for Industrial and Applied Mathematics Publications
dc.relation.ispartof SIAM Journal on Imaging Sciences
dc.rights info:eu-repo/semantics/openAccess
dc.rights.uri https://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject Structured sparsity
dc.subject Mixed norms es_PE
dc.subject Projection es_PE
dc.subject Regularization es_PE
dc.subject Root finding es_PE
dc.subject.ocde http://purl.org/pe-repo/ocde/ford#2.02.04
dc.title Efficient projection onto the ? ?,1 mixed-norm ball using a newton root search method
dc.type info:eu-repo/semantics/article
dspace.entity.type Publication
Archivos