Advances and Open Problems in Federated Learning

DOI10.1561/2200000083WikidataQ116754345 ScholiaQ116754345MaRDI QIDQ5012283

H. Brendan McMahan, Peter Kairouz

Publication date: 31 August 2021

Published in: Foundations and Trends® in Machine Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1912.04977

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

68-02: Research exposition (monographs, survey articles) pertaining to computer science

Related Items

SAMBA: A Generic Framework for Secure Federated Multi-Armed Bandits, Proximal Splitting Algorithms for Convex Optimization: A Tour of Recent Advances, with New Twists, Gradient-free federated learning methods with \(l_1\) and \(l_2\)-randomization for non-smooth convex stochastic optimization problems, Finite-time convergence rates of distributed local stochastic approximation, An accurate, scalable and verifiable protocol for federated differentially private averaging, Local2global: a distributed approach for scaling representation learning on graphs, Optimal Methods for Convex Risk-Averse Distributed Optimization, Optimal data splitting in distributed optimization for machine learning, SHED: a Newton-type algorithm for federated learning based on incremental Hessian eigenvector sharing, Coopetition against an Amazon, Decentralized personalized federated learning: lower bounds and optimal algorithm for all personalization modes, FedHD: communication-efficient federated learning from hybrid data, Network Gradient Descent Algorithm for Decentralized Federated Learning, Faster Rates for Compressed Federated Learning with Client-Variance Reduction, The more the merrier: reducing the cost of large scale MPC, Superquantiles at work: machine learning applications and efficient subgradient computation, Private aggregation from fewer anonymous messages, FL-MAC-RDP: federated learning over multiple access channels with Rényi differential privacy