Efficient Adaptive Federated Optimization
Adaptive optimization is critical in federated learning, where enabling adaptivity on both the server and client sides has proven essential for achieving optimal performance. However, the scalability of such jointly adaptive systems is often hindered by resource limitations in communication and memory. In this paper, we introduce a class of efficient adaptive algorithms, named $FedAda^2$ and its enhanced version $FedAda^2$++, designed specifically for large-scale, cross-device federated environments. $FedAda^2$ optimizes communication efficiency by avoiding the transfer of preconditioners between the server and clients. Additionally, $FedAda^2$++ extends this approach by incorporating memory-efficient adaptive optimizers on the client side, further reducing on-device memory usage. Theoretically, we demonstrate that $FedAda^2$ and $FedAda^2$++ achieve the same convergence rates for general, non-convex objectives as its more resource-intensive counterparts that directly integrate joint adaptivity. Extensive empirical evaluations on image and text datasets demonstrate both the advantages of joint adaptivity and the effectiveness of $FedAda^2$/$FedAda^2$++.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningSimilar Papers 제목 키워드 기반
FADAS: Towards Federated Adaptive Asynchronous Optimization
Federated learning (FL) has emerged as a widely adopted training paradigm for privacy-preserving machine learning. While the SGD-based FL algorithms have demonstrated considerable success in the past, there is a growing …
Federated LearningPrivacy PreservingAdaptive Federated Optimization
Federated learning is a distributed machine learning paradigm in which a large number of clients coordinate with a central server to learn a model without sharing their own training data. Standard federated optimization …
Federated LearningAccelerated Federated Learning with Decoupled Adaptive Optimization
The federated learning (FL) framework enables edge clients to collaboratively learn a shared inference model while keeping privacy of training data on clients. Recently, many heuristics efforts have been made to generali…
Federated LearningFast Adaptive Federated Bilevel Optimization
Bilevel optimization is a popular hierarchical model in machine learning, and has been widely applied to many machine learning tasks such as meta learning, hyperparameter learning and policy optimization. Although many b…
Bilevel OptimizationDistributed OptimizationMeta-LearningRepresentation LearningFaster Adaptive Momentum-Based Federated Methods for Distributed Composition Optimization
Federated Learning is a popular distributed learning paradigm in machine learning. Meanwhile, composition optimization is an effective hierarchical learning model, which appears in many machine learning applications such…
Federated LearningMeta-Learning