FedZeN: Towards superlinear zeroth-order federated learning via
incremental Hessian estimation

FedZeN: Towards superlinear zeroth-order federated learning via incremental Hessian estimation

29 September 2023

ArXiv (abs)PDF HTML

Papers citing "FedZeN: Towards superlinear zeroth-order federated learning via incremental Hessian estimation"

10 / 10 papers shown

Title
Does Federated Learning Really Need Backpropagation? Hao Feng Tianyu Pang Chao Du Wei Chen Shuicheng Yan Min Lin FedML 68 11 0 28 Jan 2023
Stochastic Zeroth Order Gradient and Hessian Estimators: Variance Reduction and Refined Bias Bounds Yasong Feng Tianyu Wang 35 13 0 29 May 2022
Desirable Companion for Vertical Federated Learning: New Zeroth-Order Gradient Based Algorithm Qingsong Zhang Bin Gu Zhiyuan Dang Cheng Deng Heng-Chiao Huang FedML 93 15 0 19 Mar 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 94 15 0 11 Feb 2022
Communication-Efficient Stochastic Zeroth-Order Optimization for Federated Learning Wenzhi Fang Ziyi Yu Yuning Jiang Yuanming Shi Colin N. Jones Yong Zhou FedML 111 60 0 24 Jan 2022
FedNL: Making Newton-Type Methods Applicable to Federated Learning M. Safaryan Rustem Islamov Xun Qian Peter Richtárik FedML 71 80 0 05 Jun 2021
A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning Sijia Liu Pin-Yu Chen B. Kailkhura Gaoyuan Zhang A. Hero III P. Varshney 72 232 0 11 Jun 2020
Inverting Gradients -- How easy is it to break privacy in federated learning? Jonas Geiping Hartmut Bauermeister Hannah Dröge Michael Moeller FedML 109 1,232 0 31 Mar 2020
Exact and Inexact Subsampled Newton Methods for Optimization Raghu Bollapragada R. Byrd J. Nocedal 64 181 0 27 Sep 2016
Communication-Efficient Learning of Deep Networks from Decentralized Data H. B. McMahan Eider Moore Daniel Ramage S. Hampson Blaise Agüera y Arcas FedML 406 17,486 0 17 Feb 2016