Distributed zeroth-order optimization: convergence rates that match centralized counterpart

DOI10.1016/J.AUTOMATICA.2023.111328MaRDI QIDQ6537281zbMATH OpenFDO

Authors Deming Yuan, Lei Wang, Alexandre Proutiere, Guodong Shi

Publication date 14 May 2024

Published in Automatica (Search for Journal in Brave)

zbMATH Keywords

optimal convergence ratedistributed optimizationzeroth-order optimizationmulti-stage optimization algorithm

Mathematics Subject Classification ID

Convex programming (90C25)

Recommendations

• Zeroth-order algorithms for stochastic distributed nonconvex optimization
• Optimal convergence rates for convex distributed optimization in networks
• Convergence of distributed gradient-tracking-based optimization algorithms with random graphs
• Distributed consensus-based multi-agent convex optimization via gradient tracking technique
• Towards accelerated rates for distributed optimization over time-varying networks

Cites work

• A distributed fixed-time optimization algorithm for multi-agent systems
• An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback
• Constrained Consensus and Optimization in Multi-Agent Networks
• Distributed Bandit Online Convex Optimization With Time-Varying Coupled Inequality Constraints
• Distributed Subgradient Methods for Multi-Agent Optimization
• Distributed subgradient-free stochastic optimization algorithm for nonsmooth convex functions over time-varying networks
• Dual Averaging for Distributed Optimization: Convergence Analysis and Network Scaling
• Exponential convergence of distributed primal-dual convex optimization algorithm without strong convexity
• Harnessing Smoothness to Accelerate Distributed Optimization
• Improved regret for zeroth-order adversarial bandit convex optimisation
• Initialization-free distributed algorithms for optimal resource allocation with feasibility constraints and application to economic dispatch of power systems
• Kernel-based methods for bandit convex optimization
• Online convex optimization in the bandit setting: gradient descent without a gradient
• Optimal Rates for Zero-Order Convex Optimization: The Power of Two Function Evaluations
• Random gradient-free minimization of convex functions
• Randomized Gradient-Free Distributed Optimization Methods for a Multiagent System With Unknown Cost Function
• ZONE: Zeroth-Order Nonconvex Multiagent Optimization Over Networks

This page was built for publication: Distributed zeroth-order optimization: convergence rates that match centralized counterpart

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6537281)