By Mikhail Belkin and others

The "double descent" risk curve was proposed to qualitatively describe the out-of-sample prediction accuracy of variably-parameterized machine learning models. This article provides a precise mathematical analysis for the shape of this curve in two simple data models with the least squares/least norm predictor. Specifically, it is shown that the risk... Show more

October 10, 2020

Loading full text...

Similar articles

Loading recommendations...

x1

Two models of double descent for weak features

Click on play to start listening