Online Program Home
My Program

Abstract Details

Activity Number: 625 - Modern Non-Parametrics
Type: Invited
Date/Time: Thursday, August 1, 2019 : 10:30 AM to 12:20 PM
Sponsor: IMS
Abstract #300082
Title: Just Interpolate: Kernel 'Ridgeless' Regression Can Generalize
Author(s): Tengyuan Liang*
Companies: University of Chicago Booth School of Business
Keywords:
Abstract:

In the absence of explicit regularization, Kernel “Ridgeless” Regression with nonlinear kernels has 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 interpolated solutions which is due to a combination of high dimensionality of the input data, curvature of the kernel function, and favorable geometric properties of the data such as an eigenvalue decay of the empirical covariance and kernel matrices. In addition to deriving a data-dependent upper bound on the out-of-sample error, we present experimental evidence suggesting that the phenomenon occurs in the MNIST dataset.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program