Uses and Abuses of the Cross-Entropy Loss: Case Studies in Modern Deep Learning

Elliott Gordon-Rodríguez, Gabriel Loaiza-Ganem, Geoff Pleiss, John P. Cunningham. Uses and Abuses of the Cross-Entropy Loss: Case Studies in Modern Deep Learning. In Jessica Zosa Forde, Francisco J. R. Ruiz, Melanie F. Pradier, Aaron Schein, editors, "I Can't Believe It's Not Better!" at NeurIPS Workshops, Virtual, December 12, 2020. Volume 137 of Proceedings of Machine Learning Research, pages 1-10, PMLR, 2020. [doi]

Abstract

Abstract is missing.