Weighted spectral algorithms under covariate shift achieve minimax rates for bounded density ratios and near-optimal rates under truncation, including misspecified targets.
Optimal learning rates for kernel conjugate gradient regression,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
stat.ML 1years
2025 1verdicts
ACCEPT 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Spectral Algorithms in Misspecified Regression: Convergence under Covariate Shift
Weighted spectral algorithms under covariate shift achieve minimax rates for bounded density ratios and near-optimal rates under truncation, including misspecified targets.