Optimal rates for plug-in estimators of density level sets

Abstract

In the context of density level set estimation, we study the convergence of general plug-in methods under two main assumptions on the density for a given level $\lambda$. More precisely, it is assumed that the density (i) is smooth in a neighborhood of $\lambda$ and (ii) has $\gamma$-exponent at level $\lambda$. Condition (i) ensures that the density can be estimated at a standard nonparametric rate and condition (ii) is similar to Tsybakov's margin assumption which is stated for the classification framework. Under these assumptions, we derive optimal rates of convergence for plug-in estimators. Explicit convergence rates are given for plug-in estimators based on kernel density estimators when the underlying measure is the Lebesgue measure. Lower bounds proving optimality of the rates in a minimax sense when the density is Hölder smooth are also provided.

Published in at http://dx.doi.org/10.3150/09-BEJ184 the Bernoulli (http://isi.cbs.nl/bernoulli/) by the International Statistical Institute/Bernoulli Society (http://isi.cbs.nl/BS/bshome.htm)

References in corpus (4)

• Fast learning rates for plug-in classifiers
• Generalization error bounds in semi-supervised classification under the cluster assumption
• Square Root Penalty: Adaptation to the Margin in Classification and in Edge Estimation
• Fast learning rates for plug-in classifiers under the margin condition

Cited by in corpus (27)

• A Unifying Review of Deep and Shallow Anomaly Detection
• Optimal weighted nearest neighbour classifiers
• Asymptotic normality of plug-in level set estimates
• Forest Density Estimation
• Asymptotics and optimal bandwidth selection for highest density region estimation
• Estimation of extreme risk regions under multivariate regular variation
• Fully adaptive density-based clustering
• Quickshift++: Provably Good Initializations for Sample-Based Mean Shift
• Adaptation to lowest density regions with application to support recovery
• Level sets estimation and Vorob'ev expectation of random compact sets
• Distribution Free Prediction Bands
• Robust Kernel Density Estimation with Median-of-Means principle
• Measuring Human Activity Spaces from GPS Data with Density Ranking and Summary Curves
• Asymptotics of Lower Dimensional Zero-Density Regions
• DBSCAN: Optimal Rates For Density Based Clustering
• Level set estimation from projection measurements: Performance guarantees and fast computation
• Minimax Hausdorff estimation of density level sets
• Asymptotics and Optimal Bandwidth for Nonparametric Estimation of Density Level Sets
• Minimum Density Hyperplanes
• Nonparametric Estimation of Surface Integrals on Level Sets
• A flexible model-free prediction-based framework for feature ranking
• The sample complexity of level set approximation
• Adaptive Hausdorff estimation of density level sets
• The empirical Christoffel function with applications in data analysis
• An Asymptotic Equivalence between the Mean-Shift Algorithm and the Cluster Tree
• Optimal rates for F-score binary classification
• A comparative simulation study of data-driven methods for estimating density level sets