Global rates of convergence in log-concave density estimation

DOI10.1214/16-AOS1480MaRDI QIDQ510698zbMATH OpenWikidataFDO

Authors Arlene K. H. Kim, Richard Samworth

Publication date 13 February 2017

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

Full work available at URL https://arxiv.org/abs/1404.2298

zbMATH Keywords

density estimationmaximum likelihood estimationlog-concavitybracketing entropyglobal loss function

Mathematics Subject Classification ID

Point estimation (62F10) Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20) Measures of information, entropy (94A17)

Abstract: The estimation of a log-concave density on $mathbb{R}^d$ represents a central problem in the area of nonparametric inference under shape constraints. In this paper, we study the performance of log-concave density estimators with respect to global loss functions, and adopt a minimax approach. We first show that no statistical procedure based on a sample of size $n$ can estimate a log-concave density with respect to the squared Hellinger loss function with supremum risk smaller than order $n^{-4/5}$, when $d=1$, and order $n^{-2/(d+1)}$ when $dgeq2$. In particular, this reveals a sense in which, when $dgeq3$, log-concave density estimation is fundamentally more challenging than the estimation of a density with two bounded derivatives (a problem to which it has been compared). Second, we show that for $dleq3$, the Hellinger $epsilon$-bracketing entropy of a class of log-concave densities with small mean and covariance matrix close to the identity grows like $maxepsilo{n}^{-d/2},epsilo{n}^{-(d-1)}$ (up to a logarithmic factor when $d=2$). This enables us to prove that when $dleq3$ the log-concave maximum likelihood estimator achieves the minimax optimal rate (up to logarithmic factors when $d=2,3$) with respect to squared Hellinger loss.

Recommendations

• Adaptation in log-concave density estimation
• Global rates of convergence of the MLEs of log-concave and \(s\)-concave densities
• Theoretical properties of the log-concave maximum likelihood estimator of a multidimensional density
• Adaptation in multivariate log-concave density estimation
• Maximum likelihood estimation of a log-concave density and its distribution function: basic properties and uniform consistency

Cited in

(39)

• 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
• Exact solutions in log-concave maximum likelihood estimation
• Inference for the mode of a log-concave density
• Editorial: Special issue on ``Nonparametric inference under shape constraints
• Some developments in the theory of shape constrained inference
• Adaptation in log-concave density estimation
• Bracketing numbers of convex and m-monotone functions on polytopes
• Adaptation in multivariate log-concave density estimation
• Methods for estimation of convex sets
• Discrete minimax estimation with trees
• A Bayesian nonparametric approach to log-concave density estimation
• 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
• Reducing Simulation Input-Model Risk via Input Model Averaging
• Univariate log-concave density estimation with symmetry or modal constraints
• Isotonic regression with unknown permutations: statistics, computation and adaptation
• Global convergence of the log-concave MLE when the true distribution is geometric
• Isotonic regression in general dimensions
• Approximations of semicontinuous functions with applications to stochastic optimization and statistical estimation
• Minimax rates for conditional density estimation via empirical entropy
• Approximation and estimation of s-concave densities via Rényi divergences
• A central limit theorem for the Hellinger loss of Grenander‐type estimators
• On convex least squares estimation when the truth is linear
• Confidence Bands for a Log-Concave Density
• Confidence intervals for multiple isotonic regression and other monotone models
• Set structured global empirical risk minimizers are rate optimal in general dimensions
• Log-concavity and strong log-concavity: a review
• Entropy of convex functions on \(\mathbb R^d\)
• How to make a neural network say ``Don't know
• scientific article; zbMATH DE number 7300702 (Why is no real title available?)
• RATE OF CONVERGENCE FOR LOGSPLINE SPECTRAL DENSITY ESTIMATION
• Bimonotone subdivisions of point configurations in the plane
• Obtaining minimax lower bounds: a review
• The limiting behavior of isotonic and convex regression estimators when the model is misspecified
• Inference for Local Parameters in Convexity Constrained Models
• Global Rate Optimality of Integral Curve Estimators in High Order Tensor Models

This page was built for publication: Global rates of convergence in log-concave density estimation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q510698)