ReliableNet trains classifiers under an explicit budget on the joint probability of high-confidence and incorrect predictions, and reports held-out certification on six benchmarks.
Title resolution pending
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
-
ReliableNet: A Chance-Constrained Approach to Trustworthy Classification in Deep Learning
ReliableNet trains classifiers under an explicit budget on the joint probability of high-confidence and incorrect predictions, and reports held-out certification on six benchmarks.