Single-seed CRPS estimates in limited-data BDL show high variance and peaks for heteroscedastic methods, with local variance correlating above 0.96 to single-seed error.
MAP, MCD, and Deep Ensembles are trained for 500 epochs using the Adam optimizer [Kingma and Ba, 2015] with learning rate 10−3 and weight decay 10−5
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Tale of Two Variances: When Single-Seed Benchmarks Fail in Bayesian Deep Learning
Single-seed CRPS estimates in limited-data BDL show high variance and peaks for heteroscedastic methods, with local variance correlating above 0.96 to single-seed error.