Federated Variance-Reduced Stochastic Gradient Descent With Robustness to Byzantine Attacks

DOI10.1109/TSP.2020.3012952OpenAlexW3046449784MaRDI QIDQ5103010FDOQ5103010

Authors: Zhaoxian Wu, Qing Ling, Tianyi Chen, Georgios B. Giannakis 

Publication date: 23 September 2022

Published in: IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1912.12716

Recommendations

• Byzantine-robust loopless stochastic variance-reduced gradient
• Gradient-free federated learning methods with \(l_1\) and \(l_2\)-randomization for non-smooth convex stochastic optimization problems
• A simplified convergence theory for Byzantine resilient stochastic gradient descent
• Federated learning for minimizing nonsmooth convex loss functions
• Robust federated learning under statistical heterogeneity via hessian-weighted aggregation
• Stochastic distributed learning with gradient quantization and double-variance reduction
• Variance-Reduced Decentralized Stochastic Optimization With Accelerated Convergence

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Cited In (5)

• Gradient-free federated learning methods with \(l_1\) and \(l_2\)-randomization for non-smooth convex stochastic optimization problems
• Byzantine-robust loopless stochastic variance-reduced gradient
• Byzantine-robust variance-reduced federated learning over distributed non-i.i.d. data
• Federated learning for minimizing nonsmooth convex loss functions
• Communication-efficient and privacy-preserving large-scale federated learning counteracting heterogeneity

This page was built for publication: Federated Variance-Reduced Stochastic Gradient Descent With Robustness to Byzantine Attacks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5103010)