When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations? (Conference Paper) | NSF PAGES

skip to main content

Citation Details

When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations?

Award ID(s):: 2031883

NSF-PAR ID:: 10248696

Author(s) / Creator(s):: Chatterji, Niladri S.; Long, Philip M.; Bartlett, Peter L.

Date Published:: 2021-01-01

Journal Name:: Proceedings of the 34th Conference on Learning Theory (COLT2021)

Format(s):: Medium: X

Sponsoring Org:: National Science Foundation

Free Publicly Accessible Full Text
Accepted Manuscript1.0
Conference Paper:
The DOI is not currently available.