A zeroth-order algorithm for distributed optimization with stochastic stripe observations

Wang, Yinghui; Zeng, Xianlin; Zhao, Wenxiao; Hong, Yiguang

doi:10.1007/s11432-022-3637-y

A zeroth-order algorithm for distributed optimization with stochastic stripe observations

Letter
Published: 14 April 2023

Volume 66, article number 199202, (2023)
Cite this article

Science China Information Sciences Aims and scope Submit manuscript

Yinghui Wang¹,
Xianlin Zeng²,
Wenxiao Zhao³ &
…
Yiguang Hong⁴

86 Accesses
3 Citations
Explore all metrics

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

References

Ram S S, Nedić A, Veeravalli V V. Distributed stochastic subgradient projection algorithms for convex optimization. J Optim Theor Appl, 2010, 147: 516–545
Article MathSciNet MATH Google Scholar
Wang Y H, Lin P, Hong Y G. Distributed regression estimation with incomplete data in multi-agent networks. Sci China Inf Sci, 2018, 61: 092202
Article MathSciNet Google Scholar
Anit K S, Dusan J, Dragana B, et al. Distributed zeroth order optimization over random networks: a Kiefer-Wolfowitz stochastic approximation approach. In: Proceedings of IEEE Conference on Decision and Control (CDC), 2018
Wang Y, Zhao W, Hong Y, et al. Distributed subgradientfree stochastic optimization algorithm for nonsmooth convex functions over time-varying networks. SIAM J Control Optim, 2019, 57: 2821–2842
Article MathSciNet MATH Google Scholar
Yuan D, Ho D W C, Xu S. Zeroth-order method for distributed optimization with approximate projections. IEEE Trans Neural Netw Learn Syst, 2015, 27: 284–294
Article MathSciNet Google Scholar
Yuan D M, Ho D W C. Randomized gradient-free method for multiagent optimization over time-varying networks. IEEE Trans Neural Netw Learn Syst, 2014, 26: 1342–1347
Article MathSciNet Google Scholar

Download references

Acknowledgements

This work was supported by National Natural Science Foundation of China (Grant Nos. 72101026, 61621063), State Key Laboratory of Intelligent Control and Decision of Complex Systems, and Fundamental Research Funds for the China Central Universities of USTB (Grant No. FRF-TP-22-141A1).

Author information

Authors and Affiliations

School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, 100083, China
Yinghui Wang
Key Laboratory of Intelligent Control and Decision of Complex Systems, School of Automation, Beijing Institute of Technology, Beijing, 100081, China
Xianlin Zeng
Key Laboratory of Systems and Control, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, 100190, China
Wenxiao Zhao
Department of Control Science and Engineering, Tongji University, Shanghai, 201804, China
Yiguang Hong

Authors

Yinghui Wang
View author publications
You can also search for this author in PubMed Google Scholar
Xianlin Zeng
View author publications
You can also search for this author in PubMed Google Scholar
Wenxiao Zhao
View author publications
You can also search for this author in PubMed Google Scholar
Yiguang Hong
View author publications
You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xianlin Zeng.

Additional information

Supporting information

Appendixes A and B. The supporting information is available online at info.scichina.com and link.springer.com. The supporting materials are published as submitted, without typesetting or editing. The responsibility for scientific accuracy and content remains entirely with the authors.

Supplementary File