FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Convergence Analysis

Abstract

Federated Learning (FL) is an emerging learning scheme that allows different distributed clients to train deep neural networks together without data sharing. Neural networks have become popular due to their unprecedented success. To the best of our knowledge, the theoretical guarantees of FL concerning neural networks with explicit forms and multi-step updates are unexplored. Nevertheless, training analysis of neural networks in FL is non-trivial for two reasons: first, the objective loss function we are optimizing is non-smooth and non-convex, and second, we are even not updating in the gradient direction. Existing convergence results for gradient descent-based methods heavily rely on the fact that the gradient direction is used for updating. This paper presents a new class of convergence analysis for FL, Federated Learning Neural Tangent Kernel (FL-NTK), which corresponds to overparamterized ReLU neural networks trained by gradient descent in FL and is inspired by the analysis in Neural Tangent Kernel (NTK). Theoretically, FL-NTK converges to a global-optimal solution at a linear rate with properly tuned learning parameters. Furthermore, with proper distributional assumptions, FL-NTK can also achieve good generalization.

arXiv commentICML 2021

References in corpus (10)

• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Federated Learning with Non-IID Data
• A Convergence Theory for Deep Learning via Over-Parameterization
• On Exact Computation with an Infinitely Wide Neural Net
• FedML: A Research Library and Benchmark for Federated Machine Learning
• FedBN: Federated Learning on Non-IID Features via Local Batch Normalization
• Bayesian Nonparametric Federated Learning of Neural Networks
• On the Convergence Rate of Training Recurrent Neural Networks
• Towards moderate overparameterization: global convergence guarantees for training shallow neural networks
• Quadratic Suffices for Over-parametrization via Matrix Chernoff Bound

Cited by in corpus (2)

• Fed-ensemble: Improving Generalization through Model Ensembling in Federated Learning
• Neural Tangent Kernel Empowered Federated Learning