Benign overfitting in linear regression

Peter L. Bartlett

doi:10.1073/pnas.1907378117

Benign overfitting in linear regression

2020-04-24

357

OA

AI

DOI：10.1073/pnas.1907378117

Original

Save

View PDF

Abstract

En 中文

The phenomenon of benign overfitting is one of the key mysteries uncovered by deep learning methodology: deep neural networks seem to predict well, even with a perfect fit to noisy training data. Motivated by this phenomenon, we consider when a perfect fit to training data in linear regression is compatible with accurate prediction. We give a characterization of linear regression problems for which the minimum norm interpolating prediction rule has near-optimal prediction accuracy. The characterization is in terms of two notions of the effective rank of the data covariance. It shows that overparameterization is essential for benign overfitting in this setting: the number of directions in parameter space that are unimportant for prediction must significantly exceed the sample size. By studying examples of data covariance properties that this characterization shows are required for benign overfitting, we find an important role for finite-dimensional data: the accuracy of the minimum norm interpolating prediction rule approaches the best possible accuracy for a much narrower range of properties of the data distribution when the data lie in an infinite-dimensional space vs. when the data lie in a finite-dimensional space with dimension that grows faster than the sample size.

Keywords:

statistical learning theory

overfitting

linear regression

interpolation

Benign overfitting in linear regression

Abstract

AI Summary

Journal

Organization

Cited Papers