Abstract
This article investigates the problem of distributed optimization over multiagent networks with the global objective being the sum of a set of possibly nonconvex functions. Based on recent developments in distributed average tracking as well as distributed extremum seeking, a distributed bounded gradient-free optimization algorithm is proposed. It is shown that the proposed scheme is able to solve nonconvex optimization problems with arbitrary prescribed accuracy. The relationship between the optimization error and control parameters is established with the error bound's explicit dependence on the bounds of agents' control inputs, which clearly demonstrates a tradeoff between the optimization error and input bound. An illustrative example is included to validate the effectiveness of proposed scheme. © 2025 IEEE.
| Original language | English |
|---|---|
| Pages (from-to) | 2560-2568 |
| Journal | IEEE Transactions on Systems, Man, and Cybernetics: Systems |
| Volume | 55 |
| Issue number | 4 |
| Online published | 16 Jan 2025 |
| DOIs | |
| Publication status | Published - Apr 2025 |
Research Keywords
- Bounded input
- extremum seeking
- gradient-free algorithm
- multiagent systems
Publisher's Copyright Statement
- COPYRIGHT TERMS OF DEPOSITED POSTPRINT FILE: © 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Du, Y., Chen, F., Xiang, L., & Feng, G. (2025). Distributed Nonconvex Optimization via Bounded Gradient-Free Inputs. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 55(4), 2560-2568. https://doi.org/10.1109/TSMC.2024.3525007
Fingerprint
Dive into the research topics of 'Distributed Nonconvex Optimization via Bounded Gradient-Free Inputs'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver