Under a Bayesian model of domain adaptation, the paper derives the optimal learner and shows that the posterior label entropy (PTLU) lower-bounds the target risk, providing a new hardness measure.
Domain adaptation--can quantity compensate for quality? Annals of Mathematics and Artificial Intelligence, 70: 0 185--202, 2014
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On the Hardness of Unsupervised Domain Adaptation: Optimal Learners and Information-Theoretic Perspective
Under a Bayesian model of domain adaptation, the paper derives the optimal learner and shows that the posterior label entropy (PTLU) lower-bounds the target risk, providing a new hardness measure.