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.
and Buettner, Florian and Huber, Wolfgang and Stegle, Oliver , year =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Embedding selection mechanisms into generative simulators enables amortized Bayesian inference to produce debiased, well-calibrated posteriors without tractable likelihoods.
Disease is framed as a perturbation ΔH to the healthy biomarker Hamiltonian H_0 = X^T X / n, with patient projections onto disease eigenmodes claimed as an optimal prognostic statistic.
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.
-
Overcoming Selection Bias in Statistical Studies With Amortized Bayesian Inference
Embedding selection mechanisms into generative simulators enables amortized Bayesian inference to produce debiased, well-calibrated posteriors without tractable likelihoods.
-
Disease Is a Spectral Perturbation
Disease is framed as a perturbation ΔH to the healthy biomarker Hamiltonian H_0 = X^T X / n, with patient projections onto disease eigenmodes claimed as an optimal prognostic statistic.