Multi-source transfer learning incurs an intrinsic adaptation cost that can exceed one, with phase transitions separating regimes where bias-agnostic estimators match oracle performance from those where they cannot.
Title resolution pending
2 Pith papers cite this work, alongside 14 external citations. Polarity classification is still indexing.
2
Pith papers citing it
14
external citations · external index
years
2026 2representative citing papers
The PROBE algorithm provably reduces the sample complexity of best-arm identification by using cheap proxy scores as control variates, achieving oracle-level savings even when the reward-proxy correlation is unknown.
citing papers explorer
-
The Statistical Cost of Adaptation in Multi-Source Transfer Learning
Multi-source transfer learning incurs an intrinsic adaptation cost that can exceed one, with phase transitions separating regimes where bias-agnostic estimators match oracle performance from those where they cannot.
-
Best-Arm Identification with Generative Proxy
The PROBE algorithm provably reduces the sample complexity of best-arm identification by using cheap proxy scores as control variates, achieving oracle-level savings even when the reward-proxy correlation is unknown.