Uniform Convergence of the Kernel Density Estimator Adaptive to Intrinsic Volume Dimension - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2019

Uniform Convergence of the Kernel Density Estimator Adaptive to Intrinsic Volume Dimension

Abstract

We derive concentration inequalities for the supremum norm of the difference between a kernel density estimator (KDE) and its point-wise expectation that hold uniformly over the selection of the bandwidth and under weaker conditions on the kernel and the data generating distribution than previously used in the literature. We first propose a novel concept, called the volume dimension, to measure the intrinsic dimension of the support of a probability distribution based on the rates of decay of the probability of vanishing Euclidean balls. Our bounds depend on the volume dimension and generalize the existing bounds derived in the literature. In particular, when the data-generating distribution has a bounded Lebesgue density or is supported on a sufficiently well-behaved lower-dimensional manifold, our bound recovers the same convergence rate depending on the intrinsic dimension of the support as ones known in the literature. At the same time, our results apply to more general cases, such as the ones of distribution with unbounded densities or supported on a mixture of manifolds with different dimensions. Analogous bounds are derived for the derivative of the KDE, of any order. Our results are generally applicable but are especially useful for problems in geometric inference and topological data analysis, including level set estimation, density-based clustering, modal clustering and mode hunting, ridge estimation and persistent homology.
Fichier principal
Vignette du fichier
arxiv.pdf (331.46 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-02404295 , version 1 (31-12-2019)

Identifiers

Cite

Jisu Kim, Jaehyeok Shin, Alessandro Rinaldo, Larry Wasserman. Uniform Convergence of the Kernel Density Estimator Adaptive to Intrinsic Volume Dimension. ICML 2019 - 36th International Conference on Machine Learning, Jun 2019, Long Beach, United States. ⟨hal-02404295⟩
75 View
265 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More