Non-smooth setting of stochastic decentralized convex optimization problem over time-varying graphs

DOI10.1007/s10287-023-00479-7arXiv2307.00392MaRDI QIDQ6060563

Aleksandr Beznosikov, Georgiy Konin, Andrew Veprikov, Dmitry P. Kovalev, Aleksandr Lobanov, A. V. Gasnikov

Publication date: 3 November 2023

Published in: Computational Management Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2307.00392

zbMATH Keywords

time-varying graphsgradient-free algorithmsnon-smooth opimizationstochastic accelerated decentralized optimization method

Mathematics Subject Classification ID

Operations research and management science (90Bxx)

Cites Work

• Unnamed Item
• Unnamed Item
• Accelerated gradient methods and dual decomposition in distributed model predictive control
• Optimal order of accuracy of search algorithms in stochastic optimization
• Distributed average consensus with least-mean-square deviation
• Estimating time-varying networks
• An accelerated directional derivative method for smooth stochastic convex optimization
• Noisy zeroth-order optimization for non-smooth saddle point problems
• Improved exploitation of higher order smoothness in derivative-free optimization
• Coordinate descent algorithms
• Stochastic online optimization. Single-point and multi-point non-linear multi-armed bandits. Convex and strongly-convex case
• Random gradient-free minimization of convex functions
• Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function
• Zeroth-order nonconvex stochastic optimization: handling constraints, high dimensionality, and saddle points
• Optimal Rates for Zero-Order Convex Optimization: The Power of Two Function Evaluations
• Average Consensus on Arbitrary Strongly Connected Digraphs With Time-Varying Topologies
• Introduction to Derivative-Free Optimization
• Fast Convergence Rates for Distributed Non-Bayesian Learning
• Derivative-Free and Blackbox Optimization
• Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs
• Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization I: A Generic Algorithmic Framework
• Kernel-based methods for bandit convex optimization
• Decentralized Accelerated Gradient Methods With Increasing Penalty Parameters
• Accelerated Distributed Nesterov Gradient Descent
• Optimal Algorithms for Non-Smooth Distributed Optimization in Networks
• An <formula formulatype="inline"><tex Notation="TeX">$O(1/k)$</tex> </formula> Gradient Method for Network Resource Allocation Problems
• An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback
• Optimal Distributed Online Prediction using Mini-Batches
• A Stochastic Approximation Method
• Gradient-free federated learning methods with \(l_1\) and \(l_2\)-randomization for non-smooth convex stochastic optimization problems
• Near-Optimal Decentralized Algorithms for Saddle Point Problems over Time-Varying Networks

This page was built for publication: Non-smooth setting of stochastic decentralized convex optimization problem over time-varying graphs