Gradient-free federated learning methods with \(l_1\) and \(l_2\)-randomization for non-smooth convex stochastic optimization problems

DOI10.1134/S0965542523090026arXiv2211.10783OpenAlexW4387620276MaRDI QIDQ6053598

D. M. Dvinskikh, A. V. Gasnikov, B. A. Alashqar, A. V. Lobanov

Publication date: 19 October 2023

Published in: Computational Mathematics and Mathematical Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2211.10783

zbMATH Keywords

inexact oraclefederated learninggradient-free methods

Mathematics Subject Classification ID

Convex programming (90C25) Stochastic programming (90C15)

Related Items (4)

Gradient-free methods for non-smooth convex stochastic optimization with heavy-tailed noise on convex compact ⋮ Non-smooth setting of stochastic decentralized convex optimization problem over time-varying graphs ⋮ Stochastic adversarial noise in the ``black box optimization problem ⋮ Accelerated zero-order SGD method for solving the black box optimization problem under ``overparametrization condition

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• An optimal method for stochastic composite optimization
• On stochastic gradient and subgradient methods with adaptive steplength sequences
• Gradient-free proximal methods with inexact oracle for convex stochastic nonsmooth optimization problems on the simplex
• An accelerated directional derivative method for smooth stochastic convex optimization
• Stochastic online optimization. Single-point and multi-point non-linear multi-armed bandits. Convex and strongly-convex case
• Randomized Smoothing for Stochastic Optimization
• Optimal Rates for Zero-Order Convex Optimization: The Power of Two Function Evaluations
• Advances and Open Problems in Federated Learning
• Finite Difference Gradient Approximation: To Randomize or Not?
• Solving variational inequalities with Stochastic Mirror-Prox algorithm
• An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback

This page was built for publication: Gradient-free federated learning methods with \(l_1\) and \(l_2\)-randomization for non-smooth convex stochastic optimization problems