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

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

10 Nov 2020NeurIPS Workshop ICBINB 2020 12arXiv:2011.05231archive 2025-07-28

Elliott Gordon-Rodriguez, Gabriel Loaiza-Ganem, Geoff Pleiss, John P. Cunningham

Modern deep learning is primarily an experimental science, in which empirical advances occasionally come at the expense of probabilistic rigor. Here we focus on one such example; namely the use of the categorical cross-entropy loss to model data that is not strictly categorical, but rather takes values on the simplex. This practice is standard in neural network architectures with label smoothing and actor-mimic reinforcement learning, amongst others. Drawing on the recently discovered continuous-categorical distribution, we propose probabilistically-inspired alternatives to these models, providing an approach that is more principled and theoretically appealing. Through careful experimentation, including an ablation study, we identify the potential for outperformance in these models, thereby highlighting the importance of a proper probabilistic treatment, as well as illustrating some of the failure modes thereof.

PaperPDFConference PDFCode

Code

cunningham-lab/cb_and_cc officialmentioned in papermentioned on GitHubtf report
cunningham-lab/cb mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Label Smoothing

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections