Spectral-Transport Stability and Benign Overfitting in Interpolating Learning

ArXi:2604.08625v1 Announce Type: cross We develop a theoretical framework for generalization in the interpolating regime of statistical learning. The central question is why highly overparameterized estimators can attain zero empirical risk while still achieving nontrivial predictive accuracy, and how to characterize the boundary between benign and destructive overfitting. We