On Optimal Learning With Random Features

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

View graph of relations

Detail(s)

Original languageEnglish
Journal / PublicationIEEE Transactions on Neural Networks and Learning Systems
Online published2 Mar 2022
Publication statusOnline published - 2 Mar 2022

Abstract

We consider supervised learning in a reproducing kernel Hilbert space (RKHS) using random features. We show that the optimal rate is obtained under suitable regularity conditions, and at the same time improving on the existing bounds on the number of random features required. As a straightforward extension, distributed learning in the simple setting of one-shot communication is also considered that achieves the same optimal rate.

Research Area(s)

  • Convergence, Distributed learning, Hilbert space, Kernel, kernel method, optimal rate, random features., Standards, Supervised learning, Time complexity, Urban areas