paper-with-me

홈 › Papers

Federated Minimax Optimization with Client Heterogeneity

2023-02-08 · Pranay Sharma, Rohan Panda, Gauri Joshi

Minimax optimization has seen a surge in interest with the advent of modern applications such as GANs, and it is inherently more challenging than simple minimization. The difficulty is exacerbated by the training data residing at multiple edge devices or \textit{clients}, especially when these clients can have heterogeneous datasets and local computation capabilities. We propose a general federated minimax optimization framework that subsumes such settings and several existing methods like Local SGDA. We show that naive aggregation of heterogeneous local progress results in optimizing a mismatched objective function -- a phenomenon previously observed in standard federated minimization. To fix this problem, we propose normalizing the client updates by the number of local steps undertaken between successive communication rounds. We analyze the convergence of the proposed algorithm for classes of nonconvex-concave and nonconvex-nonconcave functions and characterize the impact of heterogeneous client data, partial client participation, and heterogeneous local computations. Our analysis works under more general assumptions on the intra-client noise and inter-client heterogeneity than so far considered in the literature. For all the function classes considered, we significantly improve the existing computation and communication complexity results. Experimental results support our theoretical claims.

📄 PDF Abstract BibTeX arXiv:2302.04249

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Fast Decentralized Gradient Tracking for Federated Minimax Optimization with Local Updates

2024-05-07 · Chris Junchi Li

Federated learning (FL) for minimax optimization has emerged as a powerful paradigm for training models across distributed nodes/clients while preserving data privacy and model robustness on data heterogeneity. In this w…

Federated Learning

Efficient Algorithms for Federated Saddle Point Optimization

2021-02-12 · Charlie Hou, Kiran K. Thekumparampil, Giulia Fanti, Sewoong Oh

We consider strongly convex-concave minimax problems in the federated setting, where the communication constraint is the main bottleneck. When clients are arbitrarily heterogeneous, a simple Minibatch Mirror-prox achieve…

A Theorem of the Alternative for Personalized Federated Learning

2021-03-02 · Shuxiao Chen, Qinqing Zheng, Qi Long, Weijie J. Su

A widely recognized difficulty in federated learning arises from the statistical heterogeneity among clients: local datasets often come from different but not entirely unrelated distributions, and personalization is, the…

Federated LearningPersonalized Federated Learning

FedDuA: Doubly Adaptive Federated Learning

2025-05-16 · Shokichi Takakura, Seng Pei Liew, Satoshi Hasegawa

Federated learning is a distributed learning framework where clients collaboratively train a global model without sharing their raw data. FedAvg is a popular algorithm for federated learning, but it often suffers from sl…

Federated Learning

Robust Decentralized Learning with Local Updates and Gradient Tracking

2024-05-02 · Sajjad Ghiasvand, Amirhossein Reisizadeh, Mahnoosh Alizadeh, Ramtin Pedarsani

As distributed learning applications such as Federated Learning, the Internet of Things (IoT), and Edge Computing grow, it is critical to address the shortcomings of such technologies from a theoretical perspective. As a…

Adversarial RobustnessEdge-computingFederated Learning