Motivated by problems in data clustering and semi-supervised learning, we establish general conditions under which families of nonparametric mixture models are identifiable by introducing a novel framework for clustering overfitted parametric (i.e. misspecified) mixture models. These conditions generalize existing conditions in the literature, allowing for general nonparametric mixture components. Notably, our results avoid imposing assumptions […]
Identifiability of nonparametric mixture models, clustering, and semi-supervised learning