Neural Collapse with Cross-Entropy Loss

We consider the variational problem of cross-entropy loss with $n$ feature vectors on a unit hypersphere in ${\mathbb{R}}^d$. We prove that when $d \geq n - 1$, the global minimum is given by the simplex equiangular tight frame, which justifies the neural collapse behavior. We also prove that as $n \rightarrow \infty$withfixed$d$, the minimizing points will distribute uniformly on the hypersphere and show a connection with the frame potential of Benedetto & Fickus.