Consistency and convergence rate for nearest subspace classifier
Yi (Grace) Wang · Information and Inference A Journal of the IMA · 2016
The nearest subspace classifier (NSS) finds an estimation of the underlying subspace within each class and assigns data points to the class that corresponds to its nearest subspace. This paper mainly studies how well NSS can be generalized to new samples. It is proved that NSS is strongly consistent and has rate of convergence |$\mathscr {O}(n^{-1/2})$| under certain assumptions. Some simulations are presented eventually to verify the theoretical results.