How abundant are good interpolators?

August Y. Chen, Ahmed El Alaoui

Let $S$ be the set of unit norm linear classifiers $\hat{I}¸\in {\mathbb{R}}^d$ which correctly classify every point of a labeled dataset $(X_i,y_i{)}_{i=1}^n$, $X_i\in {\mathbb{R}}^d$, $y_i…