44 min
Seminar, Hosted by Simons Institute for the Theory of Computing
How abundant are good interpolators?
Cornell
Recording
Abstract
Perfectly fitting the training data does not guarantee good generalization. For two idealized data distributions, this talk characterizes how frequently linear interpolating classifiers attain a given generalization error. Large-deviation and concentration results show why typical interpolators can perform worse than solutions reached by gradient descent and motivate the problem of sampling them.