Journal article · 2022 · Open access

A distributed gradient algorithm based on randomized block-coordinate and projection-free over networks

Junlong Zhu, Xin Wang, Mingchuan Zhang, Muhua Liu, Qingtao Wu

Complex & Intelligent Systems, 9(1), 267–283 · Published 28 June 2022 · DOI 10.1007/s40747-022-00785-8

Free PDFView at the publisherCite this paper

In brief

“A distributed gradient algorithm based on randomized block-coordinate and projection-free over networks” is a 2022 journal article by Junlong Zhu and 4 co-authors, published in Complex & Intelligent Systems. OpenAlex counts 6 citations as of 15 November 2026. It is open access under a CC BY licence: the full text is free to read at Complex & Intelligent Systems.

Citations
6
Most cited in
2025 (2)
Field-weighted impact
0.34
References
60
Authors
5

Abstract

The computational bottleneck in distributed optimization methods, which is based on projected gradient descent, is due to the computation of a full gradient vector and projection step. This is a particular problem for large datasets. To reduce the computational complexity of existing methods, we combine the randomized block-coordinate descent and the Frank–Wolfe techniques, and then propose a distributed randomized block-coordinate projection-free algorithm over networks, where each agent randomly chooses a subset of the coordinates of its gradient vector and the projection step is eschewed in favor of a much simpler linear optimization step. Moreover, the convergence performance of the proposed algorithm is also theoretically analyzed. Specifically, we rigorously prove that the proposed algorithm can converge to optimal point at rate of $${\mathcal {O}}(1/t)$$ O ( 1 / t ) under convexity and $${\mathcal {O}}(1/t^2)$$ O ( 1 / t 2 ) under strong convexity, respectively. Here, t is the number of iterations. Furthermore, the proposed algorithm can converge to a stationary point, where the “Frank-Wolfe” gap is equal to zero, at a rate $${\mathcal {O}}(1/\sqrt{t})$$ O ( 1 / t ) under non-convexity. To evaluate the computational benefit of the proposed algorithm, we use the proposed algorithm to solve the multiclass classification problems by simulation experiments on two datasets, i.e., aloi and news20. The results shows that the proposed algorithm is faster than the existing distributed optimization algorithms due to its lower computation per iteration. Furthermore, the results also show that well-connected graphs or smaller graphs leads to faster convergence rate, which can confirm the theoretical results.

Cite this paper

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

APA 7

Zhu, J., Wang, X., Zhang, M., Liu, M., & Wu, Q. (2022). A distributed gradient algorithm based on randomized block-coordinate and projection-free over networks. Complex & Intelligent Systems, 9(1), 267–283. https://doi.org/10.1007/s40747-022-00785-8

MLA 9

Zhu, Junlong, et al. “A distributed gradient algorithm based on randomized block-coordinate and projection-free over networks.” Complex & Intelligent Systems, vol. 9, no. 1, 2022, pp. 267–283. https://doi.org/10.1007/s40747-022-00785-8.

Chicago

Zhu, Junlong, Xin Wang, Mingchuan Zhang, Muhua Liu, and Qingtao Wu. 2022. “A distributed gradient algorithm based on randomized block-coordinate and projection-free over networks.” Complex & Intelligent Systems 9 (1): 267–283. https://doi.org/10.1007/s40747-022-00785-8.

Harvard

Zhu, J. et al. (2022) ‘A distributed gradient algorithm based on randomized block-coordinate and projection-free over networks’, Complex & Intelligent Systems, 9(1), pp. 267–283. doi:10.1007/s40747-022-00785-8.

IEEE

J. Zhu, X. Wang, M. Zhang, M. Liu, and Q. Wu, “A distributed gradient algorithm based on randomized block-coordinate and projection-free over networks,” Complex & Intelligent Systems, vol. 9, no. 1, pp. 267–283, 2022, doi: 10.1007/s40747-022-00785-8.

BibTeX

@article{zhu2022distributed,
  title     = {{A distributed gradient algorithm based on randomized block-coordinate and projection-free over networks}},
  author    = {Zhu, Junlong and Wang, Xin and Zhang, Mingchuan and Liu, Muhua and Wu, Qingtao},
  journal   = {Complex \& Intelligent Systems},
  year      = {2022},
  volume    = {9},
  number    = {1},
  pages     = {267--283},
  doi       = {10.1007/s40747-022-00785-8},
  url       = {https://doi.org/10.1007/s40747-022-00785-8}
}

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

Citations by year

YearCitationsShare of the best year
202211
202311
202522
202622

Its field-weighted citation impact is 0.34: it has been cited 0.34 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 › Engineering › Control and Systems Engineering › Distributed Control Multi-Agent Systems

  • distributed optimization
  • randomized block coordinate descent
  • Frank-Wolfe algorithm
  • projection-free algorithms
  • projected gradient descent
  • convergence rate
  • non-convex optimization
  • multi-class classification

Work with this paper

Most-cited papers in Engineering

All highly cited Engineering papers

Questions about this paper

How do I cite this paper in APA style?

Zhu, J., Wang, X., Zhang, M., Liu, M., & Wu, Q. (2022). A distributed gradient algorithm based on randomized block-coordinate and projection-free over networks. Complex & Intelligent Systems, 9(1), 267–283. https://doi.org/10.1007/s40747-022-00785-8

How many times has this paper been cited?

6 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 Complex & Intelligent Systems.

Who wrote this paper?

Junlong Zhu, Xin Wang, Mingchuan Zhang, Muhua Liu, Qingtao Wu.

What is the DOI of this paper?

10.1007/s40747-022-00785-8. The permanent link is https://doi.org/10.1007/s40747-022-00785-8.

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.