Tengyuan Liang
Assistant Professor of Econometrics and Statistics
University of Chicago, Booth School of Business

Title: On Adaptivity, Generalization, and Interpolation Motivated from Neural Networks

Abstract:
In the absence of explicit regularization, neural network learning and kernel learning have the potential to fit the training data perfectly. It has been observed empirically, however, that such interpolated solutions can still generalize well on test data. We isolate a phenomenon of implicit regularization for minimum-norm...