Easily Parallelizable and Distributable Class of Algorithms for Structured Sparsity, with Optimal Acceleration

Many statistical learning problems can be posed as minimization of a sum of two convex functions, one typically a composition of nonsmooth and linear functions. Examples include regression under structured sparsity assumptions. Popular algorithms for solving such problems, for example, ADMM, often i...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Journal of computational and graphical statistics Ročník 28; číslo 4; s. 821 - 833
Hlavní autoři:	Ko, Seyoon, Yu, Donghyeon, Won, Joong-Ho
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Alexandria Taylor & Francis 02.10.2019 American Statistical Association, the Institute of Mathematical Statistics, and the Interface Foundation of North America Taylor & Francis Ltd
Témata:	Acceleration Advances in Sampling and Optimization Algorithms Computer networks Convergence Distributed computing Distributed processing GPU Linear functions Machine learning Monotone operator theory Nonsmooth optimization Operator splitting Optimization Parallel processing Regression analysis Sparsity Statistical analysis
ISSN:	1061-8600, 1537-2715
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!