Approximation and estimation of s-concave densities via Rényi divergences

DOI10.1214/15-AOS1408zbMATH Open1338.62105arXiv1505.00379WikidataQ42366123 ScholiaQ42366123MaRDI QIDQ292894FDOQ292894

Authors: Qiyang Han, Jon A. Wellner 

Publication date: 9 June 2016

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: In this paper, we study the approximation and estimation of $s$-concave densities via R'enyi divergence. We first show that the approximation of a probability measure $Q$ by an $s$-concave densities exists and is unique via the procedure of minimizing a divergence functional proposed by Koenker and Mizera (2010) if and only if $Q$ admits full-dimensional support and a first moment. We also show continuity of the divergence functional in $Q$: if $Q_{n}oQ$ in the Wasserstein metric, then the projected densities converge in weighted $L_1$ metrics and uniformly on closed subsets of the continuity set of the limit. Moreover, directional derivatives of the projected densities also enjoy local uniform convergence. This contains both on-the-model and off-the-model situations, and entails strong consistency of the divergence estimator of an $s$-concave density under mild conditions. One interesting and important feature for the R'enyi divergence estimator of an $s$-concave density is that the estimator is intrinsically related with the estimation of log-concave densities via maximum likelihood methods. In fact, we show that for $d=1$ at least, the R'enyi divergence estimators for $s$-concave densities converge to the maximum likelihood estimator of a log-concave density as $searrow0$. The R'enyi divergence estimator shares similar characterizations as the MLE for log-concave distributions, which allows us to develop pointwise asymptotic distribution theory assuming that the underlying density is $s$-concave.

Full work available at URL: https://arxiv.org/abs/1505.00379

Recommendations

• Shape constrained density estimation via penalized Rényi divergence
• A remark on the Grenander estimator
• Quasi-concave density estimation
• Theoretical properties of the log-concave maximum likelihood estimator of a multidimensional density
• Approximation by log-concave distributions, with applications to regression

zbMATH Keywords

consistencynonparametric estimationasymptotic distributionprojection\(s\)-concavitymode estimationshape constraints

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20) Estimation in multivariate analysis (62H12)

Cites Work

• Weak convergence and empirical processes. With applications to statistics
• Limit distribution theory for maximum likelihood estimation of a log-concave density
• Approximation by log-concave distributions, with applications to regression
• Maximum likelihood estimation of a log-concave density and its distribution function: basic properties and uniform consistency
• Convex Optimization, Shape Constraints, Compound Decisions, and Empirical Bayes Rules
• The asymptotic behavior of monotone regression estimates
• Estimation of a \(k\)-monotone density: limit distribution theory and the spline connection
• Title not available (Why is that?)
• Title not available (Why is that?)
• Detecting the Presence of Mixing with Multiscale Maximum Likelihood
• Convex measures on locally convex spaces
• Title not available (Why is that?)
• Integrals which are convex functionals. II
• Robust and efficient estimation by minimising a density power divergence
• Some remarks about the convolution of unimodal functions
• On extensions of the Brunn-Minkowski and Prekopa-Leindler theorems, including inequalities for log concave functions, and with an application to the diffusion equation
• Title not available (Why is that?)
• A note on the measurability of convex sets
• Convex set functions in d-space
• On convexity of measures
• Rates of convergence for minimum contrast estimators
• Minimax lower bounds and moduli of continuity
• Estimation of a convex function: Characterizations and asymptotic theory.
• Theoretical properties of the log-concave maximum likelihood estimator of a multidimensional density
• Global rates of convergence of the MLEs of log-concave and \(s\)-concave densities
• Approximation and estimation of \(s\)-concave densities via Rényi divergences
• Title not available (Why is that?)
• Global rates of convergence in log-concave density estimation
• Title not available (Why is that?)
• r-convex functions
• Quasi-concave density estimation
• Nonparametric estimation of multivariate convex-transformed densities
• Global risk bounds and adaptation in univariate convex regression

Cited In (21)

• Local continuity of log-concave projection, with applications to estimation under model misspecification
• High-dimensional nonparametric density estimation via symmetry and shape constraints
• Shape constrained density estimation via penalized Rényi divergence
• Inference for the mode of a log-concave density
• Variational representations and neural network estimation of Rényi divergences
• Limit distribution theory for block estimators in multiple isotonic regression
• A remark on the Grenander estimator
• A new computational framework for log-concave density estimation
• Recent progress in log-concave density estimation
• Global rates of convergence of the MLEs of log-concave and \(s\)-concave densities
• Univariate log-concave density estimation with symmetry or modal constraints
• The Modal Age of Statistics
• Oracle posterior contraction rates under hierarchical priors
• A criterion on apportionment methods minimizing the Rényi's divergence
• Approximation and estimation of \(s\)-concave densities via Rényi divergences
• A review of uncertainty quantification for density estimation
• Confidence intervals for multiple isotonic regression and other monotone models
• Set structured global empirical risk minimizers are rate optimal in general dimensions
• A Variational Characterization of Rényi Divergences
• Title not available (Why is that?)
• Inference for Local Parameters in Convexity Constrained Models

Uses Software

• Mosek
• LogConcDEAD
• logcondens

This page was built for publication: Approximation and estimation of \(s\)-concave densities via Rényi divergences

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q292894)