FLECS: a federated learning second-order framework via compression and sketching

DOI10.1080/10556788.2025.2456118MaRDI QIDQ6907518zbMATH OpenFDO

Authors Artem Agafonov, D. I. Kamzolov, Rachael Tappenden, A. V. Gasnikov, M. Takáč

Publication date 1 November 2025

Published in Optimization Methods \& Software (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/10556788.2025.2456118

Mathematics Subject Classification ID

Distributed algorithms (68W15) Large-scale problems in mathematical programming (90C06) Convex programming (90C25) Nonconvex programming, global optimization (90C26) Methods of quasi-Newton type (90C53)

Cites work

• A Newton-based method for nonconvex optimization with fast evasion of saddle points
• Communication-efficient distributed optimization of self-concordant empirical loss
• Fast Convergence Rates for Distributed Non-Bayesian Learning
• Newton Sketch: A Near Linear-Time Optimization Algorithm with Linear-Quadratic Convergence
• Numerical Optimization
• On solving L-SR1 trust-region subproblems
• Optimal scaling of a gradient method for distributed resource allocation
• Quasi-Newton methods for machine learning: forget the past, just sample
• Quasi-Newton Methods, Motivation and Theory
• Representations of quasi-Newton matrices and their use in limited memory methods
• Sketching as a tool for numerical linear algebra

This page was built for publication: FLECS: a federated learning second-order framework via compression and sketching

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6907518)