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

by   Baihe Huang, et al.

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.


page 1

page 2

page 3

page 4


Multi-Model Federated Learning with Provable Guarantees

Federated Learning (FL) is a variant of distributed learning where edge ...

Federated Learning with Nesterov Accelerated Gradient Momentum Method

Federated learning (FL) is a fast-developing technique that allows multi...

An Efficient Framework for Clustered Federated Learning

We address the problem of Federated Learning (FL) where users are distri...

Federated Latent Class Regression for Hierarchical Data

Federated Learning (FL) allows a number of agents to participate in trai...

Stochastic-Sign SGD for Federated Learning with Theoretical Guarantees

Federated learning (FL) has emerged as a prominent distributed learning ...

Federated Learning with Position-Aware Neurons

Federated Learning (FL) fuses collaborative models from local nodes with...

A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks

In distributed training of deep neural networks or Federated Learning (F...