Accelerated methods with compression for horizontal and vertical federated learning

DOI10.1007/S10957-025-02893-0MaRDI QIDQ6874621zbMATH OpenFDO

Authors Sergey Stanko, Timur Karimullin, Aleksandr Beznosikov, A. V. Gasnikov

Publication date 15 January 2026

Published in Journal of Optimization Theory and Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S10957-025-02893-0

zbMATH Keywords

accelerationcompressionhorizontal data divisionvertical data division

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Convex programming (90C25)

Cites work

• Distributed coordinate descent method for learning with big data
• Don't jump through hoops and remove those loops: SVRG and Katyusha are better without the outer loop
• Efficiency of coordinate descent methods on huge-scale optimization problems
• scientific article; zbMATH DE number 3850830 (Why is no real title available?)
• scientific article; zbMATH DE number 6982986 (Why is no real title available?)
• Katyusha: the first direct acceleration of stochastic gradient methods
• Some methods of speeding up the convergence of iteration methods
• Stochastic distributed learning with gradient quantization and double-variance reduction

This page was built for publication: Accelerated methods with compression for horizontal and vertical federated learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6874621)