Training shallow ReLU networks on noisy data using hinge loss: when do we overfit and is it benign?

Training shallow ReLU networks on noisy data using hinge loss: when do we overfit and is it benign?

Item #:: 075280-1527
UPC:

Download PDF

Details

DOI: https://doi.org/10.52202/075280-1527
Author(s): Erin George, Michael Murray, Deanna Needell, William Swartworth
Pages: 35139-35189 (51 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 36
Date/Location: Held 10-16 December 2023, New Orleans, Louisiana, USA.
Series: Advances in Neural Information Processing Systems 36
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

Description

Members/Attendees

Tab 4

Details
Description
Members/Attendees
Tab 4

DOI: https://doi.org/10.52202/075280-1527
Author(s): Erin George, Michael Murray, Deanna Needell, William Swartworth
Pages: 35139-35189 (51 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 36
Date/Location: Held 10-16 December 2023, New Orleans, Louisiana, USA.
Series: Advances in Neural Information Processing Systems 36
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)