Provably Doubly Accelerated Federated Learning: The First Theoretically
Successful Combination of Local Training and Communication Compression

Provably Doubly Accelerated Federated Learning: The First Theoretically Successful Combination of Local Training and Communication Compression

24 October 2022

Peter Richtárik

Papers citing "Provably Doubly Accelerated Federated Learning: The First Theoretically Successful Combination of Local Training and Communication Compression"

9 / 9 papers shown

Title
LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compression Laurent Condat A. Maranjyan Peter Richtárik 49 4 0 07 Mar 2024
Similarity, Compression and Local Steps: Three Pillars of Efficient Communications for Distributed Variational Inequalities Aleksandr Beznosikov Martin Takáč Alexander Gasnikov 31 10 0 15 Feb 2023
An Optimal Algorithm for Strongly Convex Min-min Optimization Alexander Gasnikov D. Kovalev Grigory Malinovsky 32 1 0 29 Dec 2022
Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Design Chuan Guo Kamalika Chaudhuri Pierre Stock Michael G. Rabbat FedML 35 7 0 08 Nov 2022
EF21 with Bells & Whistles: Practical Algorithmic Extensions of Modern Error Feedback Ilyas Fatkhullin Igor Sokolov Eduard A. Gorbunov Zhize Li Peter Richtárik 51 46 0 07 Oct 2021
A Field Guide to Federated Optimization Jianyu Wang Zachary B. Charles Zheng Xu Gauri Joshi H. B. McMahan ... Mi Zhang Tong Zhang Chunxiang Zheng Chen Zhu Wennan Zhu FedML 187 412 0 14 Jul 2021
Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients A. Mitra Rayana H. Jaafar George J. Pappas Hamed Hassani FedML 55 157 0 14 Feb 2021
Linearly Converging Error Compensated SGD Eduard A. Gorbunov D. Kovalev Dmitry Makarenko Peter Richtárik 163 78 0 23 Oct 2020
FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization Amirhossein Reisizadeh Aryan Mokhtari Hamed Hassani Ali Jadbabaie Ramtin Pedarsani FedML 176 764 0 28 Sep 2019