A fine-tuning measure is defined from the eigenvalues of a rescaled Fisher information matrix on parameter space, with a geometric interpretation as the pullback of the Euclidean metric from observable space.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
A 1-D U-Net anonymizes ECG signals by exploiting near-orthogonal privacy and utility gradients, driving re-identification to chance while preserving diagnostic AUROC.
citing papers explorer
-
Naturalness and Fisher Information
A fine-tuning measure is defined from the eigenvalues of a rescaled Fisher information matrix on parameter space, with a geometric interpretation as the pullback of the Euclidean metric from observable space.
-
REAN: Reconstruction-aware ECG Anonymization Based on Privacy--Utility Orthogonality
A 1-D U-Net anonymizes ECG signals by exploiting near-orthogonal privacy and utility gradients, driving re-identification to chance while preserving diagnostic AUROC.