paper-with-me

Papers

Momentum Benefits Non-IID Federated Learning Simply and Provably

2023-06-28 · Ziheng Cheng, Xinmeng Huang, Pengfei Wu, Kun Yuan

Federated learning is a powerful paradigm for large-scale machine learning, but it faces significant challenges due to unreliable network connections, slow communication, and substantial data heterogeneity across clients. FedAvg and SCAFFOLD are two prominent algorithms to address these challenges. In particular, FedAvg employs multiple local updates before communicating with a central server, while SCAFFOLD maintains a control variable on each client to compensate for ``client drift'' in its local updates. Various methods have been proposed to enhance the convergence of these two algorithms, but they either make impractical adjustments to the algorithmic structure or rely on the assumption of bounded data heterogeneity. This paper explores the utilization of momentum to enhance the performance of FedAvg and SCAFFOLD. When all clients participate in the training process, we demonstrate that incorporating momentum allows FedAvg to converge without relying on the assumption of bounded data heterogeneity even using a constant local learning rate. This is novel and fairly surprising as existing analyses for FedAvg require bounded data heterogeneity even with diminishing local learning rates. In partial client participation, we show that momentum enables SCAFFOLD to converge provably faster without imposing any additional assumptions. Furthermore, we use momentum to develop new variance-reduced extensions of FedAvg and SCAFFOLD, which exhibit state-of-the-art convergence rates. Our experimental results support all theoretical findings.

📄 PDF Abstract BibTeX arXiv:2306.16504

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Denoise First, Orthogonalize Later: Understanding Momentum in Muon via Spectral Filtering

2026-06-02 · Xianliang Li, Zihan Zhang, Weiyang Liu, Han Bao arxiv

Muon has recently demonstrated strong empirical performance in large language model training, but the theoretical role of momentum in Muon remains unclear. Existing analyses of Muon either remove momentum to study spectr…

SPAM: Stochastic Proximal Point Method with Momentum Variance Reduction for Non-convex Cross-Device Federated Learning

2024-05-30 · Avetik Karagulyan, Egor Shulgin, Abdurakhmon Sadiev, Peter Richtárik

Cross-device training is a crucial subfield of federated learning, where the number of clients can reach into the billions. Standard approaches and local methods are prone to issues such as client drift and insensitivity…

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

Federated Multi-Sequence Stochastic Approximation with Local Hypergradient Estimation

2023-06-02 · Davoud Ataee Tarzanagh, Mingchen Li, Pranay Sharma, Samet Oymak

Stochastic approximation with multiple coupled sequences (MSA) has found broad applications in machine learning as it encompasses a rich class of problems including bilevel optimization (BLO), multi-level compositional o…

Bilevel Optimization

Breaking the centralized barrier for cross-device federated learning

2021-12-01 · NeurIPS 2021 12 · Sai Praneeth Karimireddy, Martin Jaggi, Satyen Kale, Mehryar Mohri 외

Federated learning (FL) is a challenging setting for optimization due to the heterogeneity of the data across different clients which gives rise to the client drift phenomenon. In fact, obtaining an algorithm for FL whic…

Federated Learning