Randomized Kaczmarz in adversarial distributed setting

DOI10.1137/23M1554357zbMATH Open1545.65133MaRDI QIDQ6562376FDOQ6562376

Authors: Longxiu Huang, Xia Li, D. Needell 

Publication date: 26 June 2024

Published in: SIAM Journal on Scientific Computing (Search for Journal in Brave)

Recommendations

• Resilient penalty function method for distributed constrained optimization under Byzantine attack
• Byzantine-robust distributed sparse learning for \(M\)-estimation
• Byzantine-robust and efficient distributed sparsity learning: a surrogate composite quantile regression approach
• A resilient convex combination for consensus-based distributed algorithms
• Resilient distributed averaging: adversary detection and topological insights

zbMATH Keywords

distributed computingmode detectionrandomized Kaczmarzadversarial optimization

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Convex programming (90C25) Numerical solutions to overdetermined systems, pseudoinverses (65F20) Iterative numerical methods for linear systems (65F10)

Cites Work

• Scikit-learn: machine learning in Python
• A randomized Kaczmarz algorithm with exponential convergence
• Title not available (Why is that?)
• The mathematics of computerized tomography
• Randomized methods for linear constraints: convergence rates and conditioning
• The Relaxation Method for Linear Inequalities
• The Byzantine Generals Problem
• Single projection Kaczmarz extended algorithms
• Convergence properties of the randomized extended Gauss-Seidel and Kaczmarz methods
• Randomized Kaczmarz solver for noisy linear systems
• The Byzantine generals problem
• Title not available (Why is that?)
• On partially randomized extended Kaczmarz method for solving large sparse overdetermined inconsistent linear systems
• On greedy randomized augmented Kaczmarz method for solving large sparse inconsistent linear systems
• Solving the system of nonsingular tensor equations via randomized Kaczmarz-like method
• Median-truncated gradient descent: a robust and scalable nonconvex approach for signal estimation
• Quantile-based iterative methods for corrupted systems of linear equations
• Randomized Douglas–Rachford Methods for Linear Systems: Improved Accuracy and Efficiency

This page was built for publication: Randomized Kaczmarz in adversarial distributed setting

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6562376)