Beyond Smoothness: Incorporating Low-Rank Analysis into Nonparametric Density Estimation

Part of Advances in Neural Information Processing Systems 34 pre-proceedings (NeurIPS 2021)

Paper Supplemental

Bibtek download is not available in the pre-proceeding


Robert A. Vandermeulen, Antoine Ledent


The construction and theoretical analysis of the most popular universally consistent nonparametric density estimators hinge on one functional property: smoothness. In this paper we investigate the theoretical implications of incorporating a multi-view latent variable model, a type of low-rank model, into nonparametric density estimation. To do this we perform extensive analysis on histogram style estimators that integrate a multi-view model. Our analysis culminates in showing that there exists a universally consistent histogram style estimator that converges to any multi-view model with a finite number of Lipschitz continuous components at a rate of $\widetilde{O}(1/\sqrt[3]{n})$ in $L^1$ error, compared to the standard histogram estimator which can converge at a rate slower than $1/\sqrt[d]{n}$ on the same class of densities. Beyond this we also introduce a new type of nonparametric latent variable model based on the Tucker decomposition. A very rudimentary experimental implementation of the ideas in our paper demonstrates considerable practical improvements over the standard histogram estimator. We also provide a thorough analysis of the sample complexity of our Tucker decomposition based model. Thus, our paper provides solid first theoretical foundations for extending low-rank techniques to the nonparametric setting.