One-point feedback for composite optimization with applications to distributed and federated learning

DOI10.1080/10556788.2025.2502829MaRDI QIDQ6907537zbMATH OpenFDO

Authors Aleksandr Beznosikov, A. V. Gasnikov

Publication date 1 November 2025

Published in Optimization Methods \& Software (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/10556788.2025.2502829

Mathematics Subject Classification ID

Numerical optimization and variational techniques (65K10) Convex programming (90C25) Derivative-free methods and methods using generalized derivatives (90C56)

Cites work

• Accelerated gradient sliding for minimizing a sum of functions
• Accelerated methods for saddle-point problem
• An accelerated directional derivative method for smooth stochastic convex optimization
• An accelerated method for derivative-free smooth stochastic convex optimization
• An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback
• Decentralized Accelerated Gradient Methods With Increasing Penalty Parameters
• Decentralized and parallel primal and dual accelerated methods for stochastic convex programming problems
• Decentralized personalized federated learning: lower bounds and optimal algorithm for all personalization modes
• Distributed Subgradient Methods for Multi-Agent Optimization
• Geometric median and robust estimation in Banach spaces
• Gradient sliding for composite optimization
• scientific article; zbMATH DE number 5454133 (Why is no real title available?)
• scientific article; zbMATH DE number 3790208 (Why is no real title available?)
• Improved exploitation of higher order smoothness in derivative-free optimization
• Lectures on convex optimization
• Optimal Rates for Zero-Order Convex Optimization: The Power of Two Function Evaluations
• Oracle complexity separation in convex optimization
• Random gradient-free minimization of convex functions
• Recent theoretical advances in decentralized distributed convex optimization
• Regret analysis of stochastic and nonstochastic multi-armed bandit problems
• Solving variational inequalities with stochastic mirror-prox algorithm
• Stochastic online optimization. Single-point and multi-point non-linear multi-armed bandits. Convex and strongly-convex case

This page was built for publication: One-point feedback for composite optimization with applications to distributed and federated learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6907537)