Non-ergodic linear convergence property of the delayed gradient descent under the strongly convexity and the Polyak-Łojasiewicz condition

DOI10.1142/S0219530524500106MaRDI QIDQ6587593

Hyung Jun Choi, Jinmyoung Seok, Woocheol Choi

Publication date: 14 August 2024

Published in: Analysis and Applications (Singapore) (Search for Journal in Brave)

zbMATH Keywords

time delayconvex programminggradient descent method

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Convex programming (90C25)

Cites Work

• Online strongly convex optimization with unknown delays
• Event-triggered distributed online convex optimization with delayed bandit feedback
• Distributed asynchronous incremental subgradient methods
• Learning theory of randomized Kaczmarz algorithm
• Convex optimization: algorithms and complexity
• Decentralized Consensus Algorithm with Delayed and Stochastic Gradients
• Decentralized Online Convex Optimization With Feedback Delays
• An Asynchronous Parallel Stochastic Coordinate Descent Algorithm
• Block coordinate type methods for optimization and learning
• Federated learning for minimizing nonsmooth convex loss functions
• Online Distributed Learning for Aggregative Games With Feedback Delays

This page was built for publication: Non-ergodic linear convergence property of the delayed gradient descent under the strongly convexity and the Polyak-Łojasiewicz condition

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6587593)