Exploring Gradient Oscillation in Deep Neural Network Training

Chedi Morchdi, Yi Zhou 0017, Jie Ding 0002, Bei Wang. Exploring Gradient Oscillation in Deep Neural Network Training. In 59th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2023, Monticello, IL, USA, September 26-29, 2023. pages 1-7, IEEE, 2023. [doi]

Abstract

Abstract is missing.