Faster Rates for Federated Variational Inequalities
TL;DR · AI 摘要
Faster Rates for Federated Variational Inequalities - Apple Machine Learning Research research area Methods and Algorith...
核心要点
- 主题聚焦：Faster Rates for Federated Variational Inequalit
- 来源：Apple Machine Learning Research，建议结合原文判断细节。
- AI 分析暂不可用，本条为保底评分与摘要。
Faster Rates for Federated Variational Inequalities - Apple Machine Learning Research
research area
Methods and Algorithms
conference
NeurIPS
content type
paper
published
September 2026
Faster Rates for Federated Variational Inequalities
Authors Guanghui Wangâ **, Satyen Kale
View publication
Copy Bibtex
In this paper, we study federated optimization for solving stochastic variational inequalities (VIs), a problem that has attracted growing attention in recent years. Despite substantial progress, a significant gap remains between existing convergence rates and the state-of-the-art bounds known for federated convex optimization. In this work, we address this limitation by establishing a series of improved convergence rates. First, we show that, for general smooth and monotone variational inequalities, the classical Local Extra SGD algorithm admits tighter guarantees under a refined analysis. Next, we identify an inherent limitation of Local Extra SGD, which can lead to excessive client drift. Motivated by this observation, we propose a new algorithm, the Local Inexact Proximal Point Algorithm with Extra Step (LIPPAX), and show that it mitigates client drift and achieves improved guarantees in several regimes, including bounded Hessian, bounded operator, and low-variance settings. Finally, we extend our results to federated composite variational inequalities and establish improved convergence guarantees.
- â Georgia Institute of Technology
- ** Work done while at Apple
Related readings and updates.
Faster Rates For Federated Variational Inequalities
February 13, 2026 research area Methods and Algorithms
In this paper, we study federated optimization for solving stochastic variational inequalities (VIs), a problem that has attracted growing attention in recent years. Despite substantial progress, a significant gap remains between existing convergence rates and the state-of-the-art bounds known for federated convex optimization. In this work, we address this limitation by establishing a series of improved convergence rates. First, we show that,â¦
Read more
Improved Modelling of Federated Datasets using Mixtures-of-Dirichlet-Multinomials
June 12, 2024 research area Data Science and Annotation , research area Methods and Algorithms conference ICML
In practice, training using federated learning can be orders of magnitude slower than standard centralized training. This severely limits the amount of experimentation and tuning that can be done, making it challenging to obtain good performance on a given task. Server-side proxy data can be used to run training simulations, for instance for hyperparameter tuning. This can greatly speed up the training pipeline by reducing the number of tuningâ¦
Discover opportunities in Machine Learning.
Our research in machine learning breaks new ground every day.
Work with us