paper-with-me

홈 › Papers

FedSSO: A Federated Server-Side Second-Order Optimization Algorithm

2022-06-20 · Xin Ma, Renyi Bao, Jinpeng Jiang, Yang Liu, Arthur Jiang, Jun Yan, Xin Liu, Zhisong Pan

In this work, we propose FedSSO, a server-side second-order optimization method for federated learning (FL). In contrast to previous works in this direction, we employ a server-side approximation for the Quasi-Newton method without requiring any training data from the clients. In this way, we not only shift the computation burden from clients to server, but also eliminate the additional communication for second-order updates between clients and server entirely. We provide theoretical guarantee for convergence of our novel method, and empirically demonstrate our fast convergence and communication savings in both convex and non-convex settings.

📄 PDF Abstract BibTeX arXiv:2206.09576

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

FedPM: Federated Learning Using Second-order Optimization with Preconditioned Mixing of Local Parameters

2025-11-12 · Hiro Ishii, Kenta Niwa, Hiroshi Sawada, Akinori Fujino 외 arxiv

We propose Federated Preconditioned Mixing (FedPM), a novel Federated Learning (FL) method that leverages second-order optimization. Prior methods--such as LocalNewton, LTDA, and FedSophia--have incorporated second-order…

Federated Learning

Taming Preconditioner Drift: Unlocking the Potential of Second-Order Optimizers for Federated Learning on Non-IID Data

2026-02-22 · Junkang Liu, Fanhua Shang, Hongying Liu, Jin Liu 외 arxiv

Second-order optimizers can significantly accelerate large-scale training, yet their naive federated variants are often unstable or even diverge on non-IID data. We show that a key culprit is \emph{preconditioner drift}:…

Federated Learning

Distributed Quasi-Newton Method for Fair and Fast Federated Learning

2025-01-18 · Shayan Mohajer Hamidi, Linfeng Ye

Federated learning (FL) is a promising technology that enables edge devices/clients to collaboratively and iteratively train a machine learning model under the coordination of a central server. The most common approach t…

FairnessFederated LearningSecond-order methods

Fed-Sophia: A Communication-Efficient Second-Order Federated Learning Algorithm

2024-06-10 · Ahmed Elbakary, Chaouki Ben Issaid, Mohammad Shehab, Karim Seddik 외

Federated learning is a machine learning approach where multiple devices collaboratively learn with the help of a parameter server by sharing only their local updates. While gradient-based optimization techniques are wid…

Federated LearningSecond-order methods

Covariances for Free: Exploiting Mean Distributions for Federated Learning with Pre-Trained Models

2024-12-18 · Dipam Goswami, Simone Magistri, Kai Wang, Bartłomiej Twardowski 외

Using pre-trained models has been found to reduce the effect of data heterogeneity and speed up federated learning algorithms. Recent works have investigated the use of first-order statistics and second-order statistics …

Federated Learning