Under linear anticausal causal models, fine-tuning from UDA starts achieves target-label sample complexity proportional to the intervention dimension, not the ambient dimension.
Simultaneous analysis of lasso and dantzig selector.The Annals of Statistics, 37(4):1705, 2009
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
-
When few labeled target data suffice: a theory of semi-supervised domain adaptation via fine-tuning from multiple adaptive starts
Under linear anticausal causal models, fine-tuning from UDA starts achieves target-label sample complexity proportional to the intervention dimension, not the ambient dimension.