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.
Fast learning rates for plug-in classifiers
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
New conditions for support vector proliferation (SVP) in RKHS for bounded orthonormal systems and sub-Gaussian features, yielding generalization bounds for kernel SVMs beyond prior restrictive assumptions.
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.
-
New Equivalences Between Interpolation and SVMs: Kernels and Structured Features
New conditions for support vector proliferation (SVP) in RKHS for bounded orthonormal systems and sub-Gaussian features, yielding generalization bounds for kernel SVMs beyond prior restrictive assumptions.