Probabilistic classifiers inherit label randomness; this paper formalizes per-individual prediction variance as regret, gives a logistic-regression approximation, and tests it on loan and health datasets.
Stability and generalization analy- sis of gradient methods for shallow neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Observational Multiplicity
Probabilistic classifiers inherit label randomness; this paper formalizes per-individual prediction variance as regret, gives a logistic-regression approximation, and tests it on loan and health datasets.