Journal article · 2019 · Open access

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

Seyoon Ko, Donghyeon Yu, Joong‐Ho Won

Journal of Computational and Graphical Statistics, 28(4), 821–833 · Published 21 March 2019 · DOI 10.1080/10618600.2019.1592757

Free PDFView at the publisherCite this paper

In brief

“Easily Parallelizable and Distributable Class of Algorithms for Structured Sparsity, with Optimal Acceleration” is a 2019 journal article by Seyoon Ko and 2 co-authors, published in Journal of Computational and Graphical Statistics. OpenAlex counts 9 citations as of 15 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
9
Most cited in
2020 (4)
Field-weighted impact
1.19
References
48
Authors
3

Abstract

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 involve nontrivial optimization subproblems or smoothing approximation. We consider two classes of primal–dual algorithms that do not incur these difficulties, and unify them from a perspective of monotone operator theory. From this unification, we propose a continuum of preconditioned forward–backward operator splitting algorithms amenable to parallel and distributed computing. For the entire region of convergence of the whole continuum of algorithms, we establish its rates of convergence. For some known instances of this continuum, our analysis closes the gap in theory. We further exploit the unification to propose a continuum of accelerated algorithms. We show that the whole continuum attains the theoretically optimal rate of convergence. The scalability of the proposed algorithms, as well as their convergence behavior, is demonstrated up to 1.2 million variables with a distributed implementation. The code is available at https://github.com/kose-y/dist-primal-dual. Supplemental materials for this article are available online.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Ko, S., Yu, D., & Won, J. (2019). Easily Parallelizable and Distributable Class of Algorithms for Structured Sparsity, with Optimal Acceleration. Journal of Computational and Graphical Statistics, 28(4), 821–833. https://doi.org/10.1080/10618600.2019.1592757

MLA 9

Ko, Seyoon, et al. “Easily Parallelizable and Distributable Class of Algorithms for Structured Sparsity, with Optimal Acceleration.” Journal of Computational and Graphical Statistics, vol. 28, no. 4, 2019, pp. 821–833. https://doi.org/10.1080/10618600.2019.1592757.

Chicago

Ko, Seyoon, Donghyeon Yu, and Joong‐Ho Won. 2019. “Easily Parallelizable and Distributable Class of Algorithms for Structured Sparsity, with Optimal Acceleration.” Journal of Computational and Graphical Statistics 28 (4): 821–833. https://doi.org/10.1080/10618600.2019.1592757.

Harvard

Ko, S., Yu, D. and Won, J. (2019) ‘Easily Parallelizable and Distributable Class of Algorithms for Structured Sparsity, with Optimal Acceleration’, Journal of Computational and Graphical Statistics, 28(4), pp. 821–833. doi:10.1080/10618600.2019.1592757.

IEEE

S. Ko, D. Yu, and J. Won, “Easily Parallelizable and Distributable Class of Algorithms for Structured Sparsity, with Optimal Acceleration,” Journal of Computational and Graphical Statistics, vol. 28, no. 4, pp. 821–833, 2019, doi: 10.1080/10618600.2019.1592757.

BibTeX

@article{ko2019easily,
  title     = {{Easily Parallelizable and Distributable Class of Algorithms for Structured Sparsity, with Optimal Acceleration}},
  author    = {Ko, Seyoon and Yu, Donghyeon and Won, Joong‐Ho},
  journal   = {Journal of Computational and Graphical Statistics},
  year      = {2019},
  volume    = {28},
  number    = {4},
  pages     = {821--833},
  doi       = {10.1080/10618600.2019.1592757},
  url       = {https://doi.org/10.1080/10618600.2019.1592757}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
201911
202044
202122
202211
202611

Its field-weighted citation impact is 1.19: it has been cited 1.19 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Signal Processing › Sparse and Compressive Sensing Techniques

  • structured sparsity
  • primal-dual algorithm
  • forward-backward splitting
  • monotone operators
  • fast algorithms
  • convergence rate
  • distributed optimization
  • parallel optimization

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Ko, S., Yu, D., & Won, J. (2019). Easily Parallelizable and Distributable Class of Algorithms for Structured Sparsity, with Optimal Acceleration. Journal of Computational and Graphical Statistics, 28(4), 821–833. https://doi.org/10.1080/10618600.2019.1592757

How many times has this paper been cited?

9 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: read the free full text at arXiv (Cornell University).

Who wrote this paper?

Seyoon Ko, Donghyeon Yu, Joong‐Ho Won.

What is the DOI of this paper?

10.1080/10618600.2019.1592757. The permanent link is https://doi.org/10.1080/10618600.2019.1592757.

Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.