Design and Analysis of Distributed Multi-Agent Saddle Point Algorithm Based on Gradient-Free Oracle

In the paper, we are interested in one convex-concave function problem in network applications. Motivated by the saddle-point subgradient methods, we deal with a kind of saddle-point problem for multi-agent systems whose objective function for the underlying issue must be non-smooth but Lipschitz co...

Full description

Saved in:
Bibliographic Details
Published in2018 Australian & New Zealand Control Conference (ANZCC) pp. 362 - 365
Main Authors Wang, Chenchi, Xie, Xiangpeng
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2018
Subjects
Approximation algorithms
Convergence
Linear programming
Optimization
Prediction algorithms
Smoothing methods
Task analysis
Online AccessGet full text

Cover

More Information
Summary:In the paper, we are interested in one convex-concave function problem in network applications. Motivated by the saddle-point subgradient methods, we deal with a kind of saddle-point problem for multi-agent systems whose objective function for the underlying issue must be non-smooth but Lipschitz continuous. With the convex constrain set and global convex inequality constraints, we present a kind of distributed gradient-free algorithm in order to solve the issue of multi-agent convex-concave optimization. Under Slater's condition, We give the results of convergence rate and the effect of smoothing parameters on error bounds.
DOI:10.1109/ANZCC.2018.8606575