Spatially adaptive density estimation by localised Haar projections

DOI10.1214/12-AIHP485MaRDI QIDQ372575zbMATH OpenFDO

Authors Florian Gach, Richard Nickl, V. G. Spokoiny

Publication date 9 October 2013

Published in Annales de l'Institut Henri Poincaré. Probabilités et Statistiques (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1111.2807, https://projecteuclid.org/euclid.aihp/1372772649

zbMATH Keywords

propagation conditionspatial adaptation

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20)

Abstract: Given a random sample from some unknown density $f_0:mathbbRo[0,infty)$ we devise Haar wavelet estimators for $f_0$ with variable resolution levels constructed from localised test procedures (as in Lepski, Mammen, and Spokoiny (1997, Ann. Statist.)). We show that these estimators adapt to spatially heterogeneous smoothness of $f_0$, simultaneously for every point $x$ in a fixed interval, in sup-norm loss. The thresholding constants involved in the test procedures can be chosen in practice under the idealised assumption that the true density is locally constant in a neighborhood of the point $x$ of estimation, and an information theoretic justification of this practice is given.

Recommendations

• On Locally Adaptive Density Estimation
• Density estimation with Haar series
• scientific article; zbMATH DE number 802872
• The root-unroot algorithm for density estimation as implemented via wavelet block thresholding
• \(L^ p\) adaptive density estimation

Cites work

• scientific article; zbMATH DE number 739533 (Why is no real title available?)
• scientific article; zbMATH DE number 1552476 (Why is no real title available?)
• Adaptive estimation of a distribution function and its density in sup-norm loss by wavelet and spline projections
• An exponential inequality for the distribution function of the kernel density estimator, with applications to adaptive estimation
• Density estimation by wavelet thresholding
• Ideal spatial adaptation by wavelet shrinkage
• On the Frisch-Parisi conjecture
• Optimal spatial adaptation to inhomogeneous smoothness: An approach based on kernel estimates with variable bandwidth selectors
• Parameter tuning in pointwise adaptation using a propagation approach
• Structural adaptation via \(\mathbb L_p\)-norm oracle inequalities
• Uniform limit theorems for wavelet density estimators

Cited in

(9)

• Oracle inequalities and adaptive estimation in the convolution structure density model
• Adaptive estimation of a distribution function and its density in sup-norm loss by wavelet and spline projections
• Adaptive estimation over anisotropic functional classes via oracle approach
• Rejoinder on: ``Local quantile regression
• Locally superoptimal and adaptive projection density estimators
• Estimation error analysis of deep learning on the regression problem on the variable exponent Besov space
• Adaptation to lowest density regions with application to support recovery
• Ideal Bayesian Spatial Adaptation
• Multivariate density estimation under sup-norm loss: oracle approach, adaptation and independence structure

This page was built for publication: Spatially adaptive density estimation by localised Haar projections

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q372575)