Gossip-based gradient-free method for multi-agent optimization: Constant step size analysis

In this paper we consider a distributed constrained convex optimization problem over a network composed of multiple interacting agents. For solving this problem, we propose a gossip-based gradient-free (GGF) method that only employs local computations and interactions between agents. For a constant...

Full description

Saved in:
Bibliographic Details
Main Author: Yuan, Deming
Format: Conference Proceeding
Language:English
Subjects:
Constant Step Size
Control systems
Convergence
Convex functions
Distributed Optimization
Gossip Algorithms
Gradient-Free Method
Multi-Agent Systems
Optimization
Signal processing algorithms
Topology
Vectors
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper we consider a distributed constrained convex optimization problem over a network composed of multiple interacting agents. For solving this problem, we propose a gossip-based gradient-free (GGF) method that only employs local computations and interactions between agents. For a constant step size, we study the convergence properties of the method, and more specifically, we derive some error bounds on the expected distance from the optimal value and the expected function value; we also highlight the dependence of the error bounds on the problem parameters.
ISSN:2161-2927
DOI:10.1109/ChiCC.2014.6896825