Ridgeless Regression with Random Features

Author name not available (Why is that?)

Publication date: 1 May 2022

Abstract: Recent theoretical studies illustrated that kernel ridgeless regression can guarantee good generalization ability without an explicit regularization. In this paper, we investigate the statistical properties of ridgeless regression with random features and stochastic gradient descent. We explore the effect of factors in the stochastic gradient and random features, respectively. Specifically, random features error exhibits the double-descent curve. Motivated by the theoretical findings, we propose a tunable kernel algorithm that optimizes the spectral density of kernel during training. Our work bridges the interpolation theory and practical algorithm.

Has companion code repository: https://github.com/superlj666/ridgeless-regression-with-random-features

This page was built for publication: Ridgeless Regression with Random Features

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6397943)