Neural Tangent Kernel Empowered Federated Learning. (arXiv:2110.03681v2 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2110.03681

Federated learning (FL) is a privacy-preserving paradigm where multiple
participants jointly solve a machine learning problem without sharing raw data.
Unlike traditional distributed learning, a unique characteristic of FL is
statistical heterogeneity, namely, data distributions across participants are
different from each other. Meanwhile, recent advances in the interpretation of
neural networks have seen a wide use of neural tangent kernels (NTKs) for
convergence analyses. In this paper, we propose a novel FL paradigm empowered
by the NTK framework. The paradigm …

arxiv federated learning kernel learning neural