SHED: A Newton-type algorithm for federated learning based on
incremental Hessian eigenvector sharing

v1v2 (latest)

SHED: A Newton-type algorithm for federated learning based on incremental Hessian eigenvector sharing

11 February 2022

Nicolò Dal Fabbro

ArXiv (abs)PDF HTML

Papers citing "SHED: A Newton-type algorithm for federated learning based on incremental Hessian eigenvector sharing"

9 / 9 papers shown

Title
Accelerated Training of Federated Learning via Second-Order Methods Mrinmay Sen Sidhant R Nair C Krishna Mohan FedML 52 0 0 29 May 2025
FLeNS: Federated Learning with Enhanced Nesterov-Newton Sketch Sunny Gupta Mohit Jindal Pankhi Kashyap Pranav Jeevan Amit Sethi FedML 75 0 0 23 Sep 2024
Federated Cubic Regularized Newton Learning with Sparsification-amplified Differential Privacy Wei Huo Changxin Liu Kemi Ding Karl H. Johansson Ling Shi FedML 99 0 0 08 Aug 2024
FedNS: A Fast Sketching Newton-Type Algorithm for Federated Learning Jian Li Yong Liu Wei Wang Haoran Wu Weiping Wang FedML 83 3 0 05 Jan 2024
VREM-FL: Mobility-Aware Computation-Scheduling Co-Design for Vehicular Federated Learning Luca Ballotta Nicolò Dal Fabbro Giovanni Perin Luca Schenato Michele Rossi Giuseppe Piro 100 1 0 30 Nov 2023
Distributed Adaptive Greedy Quasi-Newton Methods with Explicit Non-asymptotic Convergence Bounds Yubo Du Keyou You 88 5 0 30 Nov 2023
FedZeN: Towards superlinear zeroth-order federated learning via incremental Hessian estimation A. Maritan S. Dey Luca Schenato FedML 90 6 0 29 Sep 2023
Q-SHED: Distributed Optimization at the Edge via Hessian Eigenvectors Quantization Nicolò Dal Fabbro M. Rossi Luca Schenato S. Dey 53 0 0 18 May 2023
Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation Rustem Islamov Xun Qian Slavomír Hanzely M. Safaryan Peter Richtárik 79 16 0 07 Jun 2022

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.