An efficient black-box reduction from PQ to TDS learning for any Boolean concept class in the distribution-free setting implies hardness for TDS learning of halfspaces, while membership queries enable efficient PQ learning of halfspaces via iterative Forster transforms.
A survey on domain adaptation theory: learning bounds and theoretical guarantees
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
The paper introduces a Markov kernel framework for exhaustively classifying corruptions in supervised learning and derives loss corrections for label, attribute, and joint cases by comparing clean and corrupted Bayes risks.
In linear regression for supervised domain adaptation, causal invariance yields finite-sample gains only when target-risk margins exceed estimation error, with matching upper and lower bounds derived and connected to structural shifts.
citing papers explorer
-
Equivalence of Coarse and Fine-Grained Models for Learning with Distribution Shift
An efficient black-box reduction from PQ to TDS learning for any Boolean concept class in the distribution-free setting implies hardness for TDS learning of halfspaces, while membership queries enable efficient PQ learning of halfspaces via iterative Forster transforms.
-
Corruptions of Supervised Learning Problems: Typology and Mitigations
The paper introduces a Markov kernel framework for exhaustively classifying corruptions in supervised learning and derives loss corrections for label, attribute, and joint cases by comparing clean and corrupted Bayes risks.
-
How Useful is Causal Invariance for Domain Adaptation in Finite-Sample Settings?
In linear regression for supervised domain adaptation, causal invariance yields finite-sample gains only when target-risk margins exceed estimation error, with matching upper and lower bounds derived and connected to structural shifts.