Generalization for multiclass classification with overparameterized linear models

no code implementations • 3 Jun 2022 • Vignesh Subramanian, Rahul Arya, Anant Sahai

Via an overparameterized linear model with Gaussian features, we provide conditions for good generalization for multiclass classification of minimum-norm interpolating solutions in an asymptotic setting where both the number of underlying features and the number of classes scale with the number of training points.

Binary Classification Classification