Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ UPCommons. Portal de...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
addClaim

Optimizing data science problems with ADMM (Alternating direction method of multipliers)

Authors: Amaré Arnàez, Pau;

Optimizing data science problems with ADMM (Alternating direction method of multipliers)

Abstract

L'Alternating Direction Method of Multipliers (ADMM) és un mètode d'optimització que permet descompondre problemes complexos en subproblemes més simples, facilitant-ne la resolució. Formalment, ADMM s’aplica a problemes d'optimització convexa amb estructura separable, combinant tècniques de multiplicadors i mètodes de descomposició. L'objectiu d’aquest treball és estudiar aquest algorisme, demostrar-ne la convergència, estendre'l a la versió amb consens i analitzar el seu comportament aplicat a dos problemes clàssics d'aprenentatge automàtic: la regressió Lasso i la classificació mitjançant Support Vector Machines (SVM). Per a fer-ho, s'ha desenvolupat l'algorisme per a cada cas en concret i s'ha aplicat a conjunt de dades sintètiques i exemples reals. En cada experiment s'han analitzat la convergència, el temps d'execució i la precisió de les solucions, i s'han comparat els resultats obtinguts amb altres mètodes o solvers coneguts. A més a més, s'han variat alguns paràmetres dels problemes per veure com l'algorisme es veu afectat.

Country
Spain
Related Organizations
Keywords

Anàlisi numèrica, Àrees temàtiques de la UPC::Matemàtiques i estadística, Support Vector Machine, Classificació AMS::65 Numerical analysis::65K Mathematical programming, optimization and variational techniques, Algorismes, Classificació AMS::90 Operations research, mathematical programming::90C Mathematical programming, Optimització Convexa, Machine learning, Aprenentatge automàtic, Operador Soft-Threshold, ADMM, Regressió Lasso, Algorithms, Numerical analysis

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green