Mixed Precision DNNs: All you need is a good parametrization

Stefan Uhlich, Lukas Mauch, Fabien Cardinaux, Kazuki Yoshiyama, Javier Alonso GarcĂ­a, Stephen Tiedemann, Thomas Kemp, Akira Nakamura. Mixed Precision DNNs: All you need is a good parametrization. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net, 2020. [doi]

Abstract

Abstract is missing.