A spectral-transport stability framework introduces the Fredriksson index to control excess risk in interpolating estimators, yielding finite-sample bounds, a sharp benign-overfitting criterion, and phase-transition rates under polynomial spectral decay.
Proceedings of the 37th Interna- tional Conference on Machine Learning 119:74–84
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Spectral-Transport Stability and Benign Overfitting in Interpolating Learning
A spectral-transport stability framework introduces the Fredriksson index to control excess risk in interpolating estimators, yielding finite-sample bounds, a sharp benign-overfitting criterion, and phase-transition rates under polynomial spectral decay.