A generalized linear risk-rewriting framework for distribution-free semi-supervised learning achieves the minimum estimator variance among a broad class and extends PNU learning to multiclass classification.
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
-
Generalized Distribution-Free Semi-Supervised Learning with Risk Rewrite
A generalized linear risk-rewriting framework for distribution-free semi-supervised learning achieves the minimum estimator variance among a broad class and extends PNU learning to multiclass classification.