Fisher8 stabilizes neural uncertainty regression by applying an output-layer natural-gradient correction with per-point normalization, improving RMSE, NLL, and ECE on UCI, weak lensing, and rotated MNIST.
Correlated input-dependent label noise in large-scale image classification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fisher8: Stabilizing Neural Heteroscedastic Regression via Output-Layer Fisher Geometry
Fisher8 stabilizes neural uncertainty regression by applying an output-layer natural-gradient correction with per-point normalization, improving RMSE, NLL, and ECE on UCI, weak lensing, and rotated MNIST.