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 Tropp, Joel A
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Feature composition in SAEs collapses asymptotically when the Gaussian mean width of the signal cone is exceeded, with ReLU inducing a ratchet-like accumulation of interference from correlations.
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.
-
Structural Instability of Feature Composition
Feature composition in SAEs collapses asymptotically when the Gaussian mean width of the signal cone is exceeded, with ReLU inducing a ratchet-like accumulation of interference from correlations.