- -

Analysis of an efficient parallel implementation of active-set Newton algorithm

RiuNet: Repositorio Institucional de la Universidad Politécnica de Valencia

Compartir/Enviar a

Citas

Estadísticas

  • Estadisticas de Uso

Analysis of an efficient parallel implementation of active-set Newton algorithm

Mostrar el registro sencillo del ítem

Ficheros en el ítem

Thumbnail
Nombre: asna-jos.pdf
Tamaño: 209.2Kb
Formato: PDF
Descripción: Versión del Autor.
Abrir
[Cerrado]
Nombre: SanJuanSebastián2 ...
Tamaño: 434.7Kb
Formato: PDF
Descripción: Versión editorial
Solicitar una copia al autor
dc.contributor.author San Juan-Sebastian, Pablo es_ES
dc.contributor.author Virtanen, T. es_ES
dc.contributor.author García Mollá, Víctor Manuel es_ES
dc.contributor.author Vidal Maciá, Antonio Manuel es_ES
dc.date.accessioned 2019-05-26T20:03:20Z
dc.date.available 2019-05-26T20:03:20Z
dc.date.issued 2018 es_ES
dc.identifier.issn 0920-8542 es_ES
dc.identifier.uri http://hdl.handle.net/10251/121116
dc.description.abstract [EN] This paper presents an analysis of an efficient parallel implementation of the active-set Newton algorithm (ASNA), which is used to estimate the nonnegative weights of linear combinations of the atoms in a large-scale dictionary to approximate an observation vector by minimizing the Kullback¿Leibler divergence between the observation vector and the approximation. The performance of ASNA has been proved in previous works against other state-of-the-art methods. The implementations analysed in this paper have been developed in C, using parallel programming techniques to obtain a better performance in multicore architectures than the original MATLAB implementation. Also a hardware analysis is performed to check the influence of CPU frequency and number of CPU cores in the different implementations proposed. The new implementations allow ASNA algorithm to tackle real-time problems due to the execution time reduction obtained. es_ES
dc.description.sponsorship This work has been partially supported by Programa de FPU del MECD, by MINECO and FEDER from Spain, under the projects TEC2015-67387- C4-1-R, and by project PROMETEO FASE II 2014/003 of Generalitat Valenciana. The authors want to thank Dr. Konstantinos Drossos for some very useful mind changing discussions. This work has been conducted in Laboratory of Signal Processing, Tampere University of Technology. es_ES
dc.language Inglés es_ES
dc.publisher Springer-Verlag es_ES
dc.relation.ispartof The Journal of Supercomputing es_ES
dc.rights Reserva de todos los derechos es_ES
dc.subject Newton algorithm es_ES
dc.subject Convex optimization es_ES
dc.subject Sparse representation es_ES
dc.subject Multicore Parallel computing es_ES
dc.subject.classification CIENCIAS DE LA COMPUTACION E INTELIGENCIA ARTIFICIAL es_ES
dc.title Analysis of an efficient parallel implementation of active-set Newton algorithm es_ES
dc.type Artículo es_ES
dc.identifier.doi 10.1007/s11227-018-2423-5 es_ES
dc.relation.projectID info:eu-repo/grantAgreement/MECD//FPU13%2F03828/ES/FPU13%2F03828/ es_ES
dc.relation.projectID info:eu-repo/grantAgreement/MINECO//TEC2015-67387-C4-1-R/ES/SMART SOUND PROCESSING FOR THE DIGITAL LIVING/ es_ES
dc.relation.projectID info:eu-repo/grantAgreement/GVA//PROMETEOII%2F2014%2F003/ES/Computación y comunicaciones de altas prestaciones y aplicaciones en ingeniería/ es_ES
dc.rights.accessRights Abierto es_ES
dc.contributor.affiliation Universitat Politècnica de València. Departamento de Sistemas Informáticos y Computación - Departament de Sistemes Informàtics i Computació es_ES
dc.description.bibliographicCitation San Juan-Sebastian, P.; Virtanen, T.; García Mollá, VM.; Vidal Maciá, AM. (2018). Analysis of an efficient parallel implementation of active-set Newton algorithm. The Journal of Supercomputing. 75(3):1298-1309. https://doi.org/10.1007/s11227-018-2423-5 es_ES
dc.description.accrualMethod S es_ES
dc.relation.publisherversion http://doi.org/10.1007/s11227-018-2423-5 es_ES
dc.description.upvformatpinicio 1298 es_ES
dc.description.upvformatpfin 1309 es_ES
dc.type.version info:eu-repo/semantics/publishedVersion es_ES
dc.description.volume 75 es_ES
dc.description.issue 3 es_ES
dc.relation.pasarela S\369008 es_ES
dc.contributor.funder Generalitat Valenciana es_ES
dc.contributor.funder Ministerio de Educación es_ES
dc.contributor.funder Ministerio de Economía y Empresa es_ES
dc.description.references Raj B, Smaragdis P (2005) Latent variable decomposition of spectrograms for single channel speaker separation. In: Proceedings of the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA 2005), New Paltz, Ny es_ES
dc.description.references Bertin N, Badeau R, Vincent E (2010) Enforcing harmonicity and smoothness in Bayesian non-negative matrix factorization applied to polyphonic music transcription. IEEE Trans Audio Speech Lang Process 18(3):538–549 es_ES
dc.description.references Dikmen O, Mesaros A (2013) Sound event detection using non-negative dictionaries learned from annotated overlapping events. In: IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA 2013). New Paltz, NY es_ES
dc.description.references Lawson CL, Hanson RJ (1995) Solving least squares problems. Society for Industrial and Applied Mathematics, Philadelphia es_ES
dc.description.references Virtanen T (2007) Monaural sound source separation by nonnegative matrix factorization with temporal continuity and sparseness criteria. IEEE Trans Audio Speech Lang Process 15(3):1066–1074 es_ES
dc.description.references Virtanen T, Gemmeke J, Raj B (2013) Active-set Newton algorithm for overcomplete non-negative representations of audio. IEEE Trans Audio Speech Lang Process 21(11):2277–2289 es_ES
dc.description.references Cemgil AT (2009) Bayesian inference for nonnegative matrix factorisation models. Comput Intell Neurosci 2009:785152 es_ES
dc.description.references Cichocki A, Zdunek R, Phan AH, Amari S (2009) Nonnegative matrix and tensor factorizations. Wiley, New York es_ES
dc.description.references MATLAB (2014) The Mathworks Inc., MATLAB R2014B, Natnick MA es_ES
dc.description.references Tuomas Virtanen, Original MATLAB implementation of ASNA algorithm. http://www.cs.tut.fi/~tuomasv/software.html es_ES
dc.description.references Carabias-Orti J, Rodriguez-Serrano F, Vera-Candeas P, Canadas-Quesada F, Ruiz-Reyes N (2013) Constrained non-negative sparse coding using learnt instrument templates for realtime music transcription. Eng Appl Artif Intell 26:1671–1680 es_ES
dc.description.references San Juan P, Virtanen T, Garcia-Molla Victor M, Vidal Antonio M (2016) Efficient parallel implementation of active-set newton algorithm for non-negative sparse representations. In: 16th International Conference on Computational and Mathematical Methods in Science and Engineering (CMMSE 2016), Rota, Spain es_ES
dc.description.references Juan P San, Efficient implementations of ASNA algorithm. https://gitlab.com/P.SanJuan/ASNA es_ES
dc.description.references OpenMP v4.5 specification (2015). http://www.openmp.org/wpcontent/uploads/openmp-4.5.pdf es_ES
dc.description.references Gemmeke JF, Hurmalainen A, Virtanen T, Sun Y (2011) Toward a practical implementation of exemplar-based noise robust ASR. In: Signal Processing Conference, 19th European, IEEE, pp 1490–1494 es_ES


Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem