Mini-Workshop: Interpolation and Over-parameterization in Statistics and Machine Learning

Abstract

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, this phenomenon of "benign overfitting'' or "harmless interpolation'' seems to be close to the practical regimes of modern deep learning systems, and, arguably, underlies many of their behaviors. This workshop brought together experts on the emerging theory of interpolation in statistical methods, its theoretical foundations and applications to machine learning and deep learning.