Benign overfitting, a phenomenon where deep neural networks predict well despite perfectly
fitting noisy training data, challenges classical statistical intuition, which suggests a tradeoff …

Contemporary machine learning systems have demonstrated tremendous success at a
variety of tasks including image classification, object detection and tracking, and …

In recent years it has become clear that, contrary to traditional statistical beliefs, methods that
interpolate (fit exactly) the noisy training data, can still be statistically optimal. In particular …