paper-with-me

홈 › Papers

Refined Analysis of Federated Averaging's Bias and Federated Richardson-Romberg Extrapolation

2024-12-02 · Paul Mangold, Alain Durmus, Aymeric Dieuleveut, Sergey Samsonov, Eric Moulines

In this paper, we present a novel analysis of FedAvg with constant step size, relying on the Markov property of the underlying process. We demonstrate that the global iterates of the algorithm converge to a stationary distribution and analyze its resulting bias and variance relative to the problem's solution. We provide a first-order expansion of the bias in both homogeneous and heterogeneous settings. Interestingly, this bias decomposes into two distinct components: one that depends solely on stochastic gradient noise and another on client heterogeneity. Finally, we introduce a new algorithm based on the Richardson-Romberg extrapolation technique to mitigate this bias.

📄 PDF Abstract BibTeX arXiv:2412.01389

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On Principled Local Optimization Methods for Federated Learning

2024-01-24 · Honglin Yuan

Federated Learning (FL), a distributed learning paradigm that scales on-device learning collaboratively, has emerged as a promising approach for decentralized AI applications. Local optimization methods such as Federated…

Federated Learning

Faster On-Device Training Using New Federated Momentum Algorithm

2020-02-06 · Zhouyuan Huo, Qian Yang, Bin Gu, Lawrence Carin. Heng Huang

Mobile crowdsensing has gained significant attention in recent years and has become a critical paradigm for emerging Internet of Things applications. The sensing devices continuously generate a significant quantity of da…

Federated Learning

Federated Causal Inference in Healthcare: Methods, Challenges, and Applications

2025-05-04 · Haoyang Li, Jie Xu, Kyra Gan, Fei Wang 외

Federated causal inference enables multi-site treatment effect estimation without sharing individual-level data, offering a privacy-preserving solution for real-world evidence generation. However, data heterogeneity acro…

Causal InferencePrivacy Preserving

FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregation

2022-12-14 · Ziqing Fan, Yanfeng Wang, Jiangchao Yao, Lingjuan Lyu 외

The statistical heterogeneity of the non-independent and identically distributed (non-IID) data in local clients significantly limits the performance of federated learning. Previous attempts like FedProx, SCAFFOLD, MOON,…

Federated Learning

FedCM: Federated Learning with Client-level Momentum

2021-06-21 · Jing Xu, Sen Wang, LiWei Wang, Andrew Chi-Chih Yao

Federated Learning is a distributed machine learning approach which enables model training without data sharing. In this paper, we propose a new federated learning algorithm, Federated Averaging with Client-level Momentu…

Federated Learning