Weighted spectral algorithms with clipped importance weights achieve rates arbitrarily close to the optimal capacity-dependent rates under covariate shift with unbounded density ratios.
On regularization algorithms in learning theory
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
-
Spectral Algorithms under Covariate Shift
Weighted spectral algorithms with clipped importance weights achieve rates arbitrarily close to the optimal capacity-dependent rates under covariate shift with unbounded density ratios.