A two-step estimator transfers a black-box predictor's knowledge across mismatched feature spaces, with risk bounds that beat non-transfer learning when the residual component is small or smooth.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Black-Box Knowledge Transfer across Distinct Feature Sets
A two-step estimator transfers a black-box predictor's knowledge across mismatched feature spaces, with risk bounds that beat non-transfer learning when the residual component is small or smooth.