Federated learning for minimizing nonsmooth convex loss functions

DOI10.3934/mfc.2023026zbMath1527.68200OpenAlexW4380685566MaRDI QIDQ6112869

No author found.

Publication date: 7 August 2023

Published in: Mathematical Foundations of Computing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.3934/mfc.2023026

zbMATH Keywords

Gaussian approximationapproximating sequencelearning ratefederated learningzeroth-order gradient

Mathematics Subject Classification ID

Convex programming (90C25) Learning and adaptive systems in artificial intelligence (68T05) Stochastic programming (90C15) Privacy of data (68P27)

Cites Work

• Unregularized online learning algorithms with general loss functions
• Online gradient descent learning algorithms
• Modified Fejér sequences and applications
• Convergence of online mirror descent
• Random gradient-free minimization of convex functions
• Optimal Rates for Zero-Order Convex Optimization: The Power of Two Function Evaluations
• ONLINE LEARNING WITH MARKOV SAMPLING
• On Stochastic Subgradient Mirror-Descent Algorithm with Weighted Averaging
• Convergence analysis of distributed multi-penalty regularized pairwise learning
• Gradient‐free method for distributed multi‐agent optimization via push‐sum algorithms
• Analysis of Online Composite Mirror Descent Algorithm
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
• Distributed Mirror Descent for Online Composite Optimization