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.
A survey of transfer learning
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Provides a finite-sample minimax characterization of black-box assisted regression with a phase transition at δ_c(n) ~ n^{-β/(2β+d)} and a safe residual estimator achieving near-optimal risk.
FT-MDN-Transformer improves transfer learning for loan recovery rate prediction under covariate, conditional, and label shifts with heterogeneous features, outperforming baselines when target data is limited.
CALM learns embeddings to align mismatched covariates between RCTs and observational studies, transfers outcome models, and calibrates them on trial data to improve CATE estimation without imputation.
CDLF applies conditional diffusion models to produce probabilistic life-cycle forecasts for new products by conditioning on static descriptors and reference trajectories from similar items.
Deep learning models on standardized 2D CT projections of pelvis and skull from 141 cadavers reach 95.65% patient-level accuracy for biological sex determination.
Transfer learning from PREDICT v3 and de-novo random survival forests improve calibration of five-year breast cancer survival predictions over the baseline in MA.27 data while handling missing information, with benefits seen in SEER but not TEAM validation.
A survey that organizes methods for cross-domain object detection into a taxonomy, analyzes domain shift across detection stages, and outlines persistent challenges.
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.