Zeroth-order algorithms for stochastic distributed nonconvex optimization

DOI10.1016/j.automatica.2022.110353zbMath1494.93146arXiv2106.02958OpenAlexW3171374256MaRDI QIDQ2151863

Shengjun Zhang, Karl Henrik Johansson, Xinlei Yi, Tao Yang

Publication date: 5 July 2022

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2106.02958

zbMATH Keywords

stochastic optimizationlinear speedupgradient-freePolyak-Łojasiewicz conditiondistributed nonconvex optimization

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Optimal stochastic control (93E20)

Uses Software

• WEDGE

Cites Work

• On the information-adaptive variants of the ADMM: an iteration complexity perspective
• A stochastic subspace approach to gradient-free optimization in high dimensions
• A new one-point residual-feedback oracle for black-box learning and control
• Restricted strong convexity and its applications to convergence analysis of gradient-type methods in convex optimization
• Random gradient-free minimization of convex functions
• Random optimization
• Optimal Rates for Zero-Order Convex Optimization: The Power of Two Function Evaluations
• Self-Correcting Geometry in Model-Based Algorithms for Derivative-Free Unconstrained Optimization
• Introduction to Derivative-Free Optimization
• `` Direct Search Solution of Numerical and Statistical Problems
• Derivative-Free and Blackbox Optimization
• Harnessing Smoothness to Accelerate Distributed Optimization
• Stochastic Three Points Method for Unconstrained Smooth Minimization
• Distributed Subgradient Methods for Multi-Agent Optimization
• Distributed Randomized Gradient-Free Mirror Descent Algorithm for Constrained Optimization
• Accelerated Distributed Nesterov Gradient Descent
• Global Convergence of General Derivative-Free Trust-Region Algorithms to First- and Second-Order Critical Points
• ZONE: Zeroth-Order Nonconvex Multiagent Optimization Over Networks
• Randomized Gradient-Free Distributed Optimization Methods for a Multiagent System With Unknown Cost Function
• Derivative-free optimization methods
• Distributed Subgradient-Free Stochastic Optimization Algorithm for Nonsmooth Convex Functions over Time-Varying Networks
• EXTRA: An Exact First-Order Algorithm for Decentralized Consensus Optimization
• Gradient‐free method for distributed multi‐agent optimization via push‐sum algorithms
• An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
• A Simplex Method for Function Minimization
• Distributed Zero-Order Algorithms for Nonconvex Multiagent Optimization
• Wedge trust region method for derivative free optimization.
• Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization

This page was built for publication: Zeroth-order algorithms for stochastic distributed nonconvex optimization