Distributed Second Order Methods with Fast Rates and Compressed Communication

14 February 2021

Papers citing "Distributed Second Order Methods with Fast Rates and Compressed Communication"

26 / 26 papers shown

Title
GP-FL: Model-Based Hessian Estimation for Second-Order Over-the-Air Federated Learning Shayan Mohajer Hamidi Ali Bereyhi S. Asaad H. Vincent Poor 62 1 0 05 Dec 2024
Natural Policy Gradient and Actor Critic Methods for Constrained Multi-Task Reinforcement Learning Sihan Zeng Thinh T. Doan Justin Romberg 19 0 0 03 May 2024
Distributed Adaptive Greedy Quasi-Newton Methods with Explicit Non-asymptotic Convergence Bounds Yubo Du Keyou You 39 4 0 30 Nov 2023
FedECA: A Federated External Control Arm Method for Causal Inference with Time-To-Event Data in Distributed Settings Jean Ogier du Terrail Quentin Klopfenstein Honghao Li Imke Mayer Nicolas Loiseau Mohammad Hallal Félix Balazard M. Andreux 14 2 0 28 Nov 2023
Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates Ahmad Rammal Kaja Gruntkowska Nikita Fedin Eduard A. Gorbunov Peter Richtárik 32 5 0 15 Oct 2023
Improved Communication Efficiency in Federated Natural Policy Gradient via ADMM-based Gradient Updates Guangchen Lan Han Wang James Anderson Christopher G. Brinton Vaneet Aggarwal FedML 11 27 0 09 Oct 2023
Efficient Federated Learning via Local Adaptive Amended Optimizer with Linear Speedup Yan Sun Li Shen Hao Sun Liang Ding Dacheng Tao FedML 19 16 0 30 Jul 2023
Towards a Better Theoretical Understanding of Independent Subnetwork Training Egor Shulgin Peter Richtárik AI4CE 16 6 0 28 Jun 2023
Communication Acceleration of Local Gradient Methods via an Accelerated Primal-Dual Algorithm with Inexact Prox Abdurakhmon Sadiev D. Kovalev Peter Richtárik 15 20 0 08 Jul 2022
FedSSO: A Federated Server-Side Second-Order Optimization Algorithm Xinteng Ma Renyi Bao Jinpeng Jiang Yang Liu Arthur Jiang Junhua Yan Xin Liu Zhisong Pan FedML 13 6 0 20 Jun 2022
Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation Rustem Islamov Xun Qian Slavomír Hanzely M. Safaryan Peter Richtárik 22 16 0 07 Jun 2022
Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top Eduard A. Gorbunov Samuel Horváth Peter Richtárik Gauthier Gidel AAML 16 0 0 01 Jun 2022
Hessian Averaging in Stochastic Newton Methods Achieves Superlinear Convergence Sen Na Michal Derezinski Michael W. Mahoney 14 16 0 20 Apr 2022
SHED: A Newton-type algorithm for federated learning based on incremental Hessian eigenvector sharing Nicolò Dal Fabbro S. Dey M. Rossi Luca Schenato FedML 21 14 0 11 Feb 2022
Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning Xun Qian Rustem Islamov M. Safaryan Peter Richtárik FedML 8 23 0 02 Nov 2021
Distributed Principal Component Analysis with Limited Communication Foivos Alimisis Peter Davies Bart Vandereycken Dan Alistarh 19 11 0 27 Oct 2021
What Do We Mean by Generalization in Federated Learning? Honglin Yuan Warren Morningstar Lin Ning K. Singhal OOD FedML 15 71 0 27 Oct 2021
A Stochastic Newton Algorithm for Distributed Convex Optimization Brian Bullins Kumar Kshitij Patel Ohad Shamir Nathan Srebro Blake E. Woodworth 16 15 0 07 Oct 2021
EF21 with Bells & Whistles: Practical Algorithmic Extensions of Modern Error Feedback Ilyas Fatkhullin Igor Sokolov Eduard A. Gorbunov Zhize Li Peter Richtárik 42 44 0 07 Oct 2021
On Second-order Optimization Methods for Federated Learning Sebastian Bischoff Stephan Günnemann Martin Jaggi Sebastian U. Stich FedML 16 10 0 06 Sep 2021
EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback Peter Richtárik Igor Sokolov Ilyas Fatkhullin 15 138 0 09 Jun 2021
FedNL: Making Newton-Type Methods Applicable to Federated Learning M. Safaryan Rustem Islamov Xun Qian Peter Richtárik FedML 14 77 0 05 Jun 2021
Communication-Efficient Distributed Optimization with Quantized Preconditioners Foivos Alimisis Peter Davies Dan Alistarh 11 15 0 14 Feb 2021
Towards Tight Communication Lower Bounds for Distributed Optimisation Dan Alistarh Janne H. Korhonen FedML 12 6 0 16 Oct 2020
Differentially Quantized Gradient Methods Chung-Yi Lin V. Kostina B. Hassibi MQ 12 7 0 06 Feb 2020
A Proximal Stochastic Gradient Method with Progressive Variance Reduction Lin Xiao Tong Zhang ODL 76 736 0 19 Mar 2014