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 Hall, Georgina , number =
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
Establishes n^{1-ε}-hardness of approximation for dichromatic number and acyclic number on tournaments, plus polynomial-time approximations for ℓ-dicolorable digraphs and special dense cases.
Two methods achieve vanishing misclassification for community detection in directed mean-field binary graphical models when T ≫ N (near-optimal), and exact recovery when T ≫ N², without knowing edge probability p.
Develops a toolbox for two-to-infinity norm bounds on eigenvector deviations under multiple assumption sets and derives generic conditions for perfect clustering
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.
-
Hardness and Approximation for Coloring Digraphs
Establishes n^{1-ε}-hardness of approximation for dichromatic number and acyclic number on tournaments, plus polynomial-time approximations for ℓ-dicolorable digraphs and special dense cases.
-
Community detection for binary graphical models in high dimension
Two methods achieve vanishing misclassification for community detection in directed mean-field binary graphical models when T ≫ N (near-optimal), and exact recovery when T ≫ N², without knowing edge probability p.
-
Davis-Kahan Theorem in the two-to-infinity norm and its application to perfect clustering
Develops a toolbox for two-to-infinity norm bounds on eigenvector deviations under multiple assumption sets and derives generic conditions for perfect clustering