Faster Rates for Federated Variational Inequalities
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 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.
- Next, we identify an inherent limitation of Local Extra SGD, which can lead to excessive client drift.
- Apple Machine Learning Research research area Methods and Algorithms conference NeurIPS content type paper published September 2026 Faster Rates for Federated Variational Inequalities 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. 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,… 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 tuning… Discover opportunities in Machine Learning. Our research in machine learning breaks new ground every day.
Sources
Related stories
Model Auditing: Faithfulness of Post-hoc Explanations Investigated
A study published on arXiv cs.CV investigates the faithfulness of post-hoc explanations for a pedestrian detection model across different domains.
DeskForge Corpus Improves Computer-Use Agent Accuracy
A new corpus of annotated desktop observations, DeskForge, enables computer-use agents to achieve higher accuracy in complex desktop scenes.
Microsoft's DeBERTa-v3-small Beats RoBERTa Using Half the Parameters
Takeaways − DeBERTa-v3-small is a 44M-parameter English encoder with a 128K vocabulary from Microsoft Research. Uses ELECTRA-style replaced-token-detection training instead of masked language modeling for better sample efficiency.
arXiv imposes rate limit on paper submissions to stem the AI slop tide
arXiv, the preprint paper repository, is seeing so many low-quality submissions, with AI tools helping drive the surge, that it has imposed a hard limit of…