Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)

This is a publication. If there is no link to the publication on this page, you can try the pre-formated search via the search engines listed on this page.

Authors: Zhenyu Zhu, Fanghui Liu, Grigorios Chrysos, Volkan Cevher

Journal title: Advances in Neural Information Processing Systems 35 (NeurIPS 2022)

Journal number: November 28-December 3, 2022

Journal publisher: NeurIPS

Published year: 2022