- Peter Bartlett
- Phil Long

## Abstract

We consider bounds on the generalization ability of the least-norm linear regressor, in the over-parameterized regime where it can interpolate the data. We describe a sense in which any generalization bound of a type that is commonly proved in statistical learning theory must sometimes be very loose when applied to analyze the least-norm interpolant. In particular, for a variety of natural joint distributions on training examples, any valid generalization bound that depends only on the output of the learning algorithm, the number of training examples, and the confidence parameter, and that satisfies a mild condition (substantially weaker than monotonicity in sample size), must sometimes be very loose βit can be bounded below by a constant when the true excess risk goes to zero.

## Research Areas

### Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work