Fast multivariate log-concave density estimation

DOI10.1016/J.CSDA.2019.04.005MaRDI QIDQ2337320zbMATH OpenOpenAlexWikidataFDO

Authors Fabian Rathke, Christoph Schnörr

Publication date 19 November 2019

Published in Computational Statistics and Data Analysis (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1805.07272

zbMATH Keywords

maximum likelihood estimationnonparametric density estimationlog-concavityadaptive piecewise-affine parametrization

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Density estimation (62G07) Software, source code, etc. for problems pertaining to statistics (62-04)

Abstract: A novel computational approach to log-concave density estimation is proposed. Previous approaches utilize the piecewise-affine parametrization of the density induced by the given sample set. The number of parameters as well as non-smooth subgradient-based convex optimization for determining the maximum likelihood density estimate cause long runtimes for dimensions $dgeq2$ and large sample sets. The presented approach is based on mildly non-convex smooth approximations of the objective function and extit{sparse}, adaptive piecewise-affine density parametrization. Established memory-efficient numerical optimization techniques enable to process larger data sets for dimensions $dgeq2$. While there is no guarantee that the algorithm returns the maximum likelihood estimate for every problem instance, we provide comprehensive numerical evidence that it does yield near-optimal results after significantly shorter runtimes. For example, 10000 samples in $mathbb{R}^2$ are processed in two seconds, rather than in $approx14$ hours required by the previous approach to terminate. For higher dimensions, density estimation becomes tractable as well: Processing $10000$ samples in $mathbb{R}^6$ requires 35 minutes. The software is publicly available as CRAN R package fmlogcondens.

Recommendations

• A computational approach to log-concave density estimation
• Maximum likelihood estimation of a multi-dimensional log-concave density. With discussion and authors' reply
• A fast algorithm for univariate log-concave density estimation
• Computing maximum likelihood estimators of a log-concave density function
• Adaptation in multivariate log-concave density estimation

Cites work

• scientific article; zbMATH DE number 3567782 (Why is no real title available?)
• scientific article; zbMATH DE number 5060482 (Why is no real title available?)
• A modified BFGS method and its global convergence in nonconvex minimization
• Computational results of an \(O^{\ast }(n^{4})\) volume algorithm
• Higher-dimensional Voronoi diagrams in linear expected time
• Hit-and-run for numerical integration
• Invariant Integration Formulas for the n-Simplex by Combinatorial Methods
• Maximum likelihood estimation of a log-concave density and its distribution function: basic properties and uniform consistency
• Maximum likelihood estimation of a multi-dimensional log-concave density. With discussion and authors' reply
• On the estimation of a probability density function by the maximum penalized likelihood method
• Recent progress in log-concave density estimation
• Sample-optimal density estimation in nearly-linear time
• Smoothed log-concave maximum likelihood estimation with applications
• Sparse grids
• The geometry of logconcave functions and sampling algorithms
• The maximum numbers of faces of a convex polytope
• The quickhull algorithm for convex hulls

Cited in

(12)

• High-dimensional nonparametric density estimation via symmetry and shape constraints
• Exact solutions in log-concave maximum likelihood estimation
• Nonparametric density estimation and bandwidth selection with B-spline bases: a novel Galerkin method
• A fast algorithm for univariate log-concave density estimation
• A new computational framework for log-concave density estimation
• Maximum likelihood estimation of a multi-dimensional log-concave density. With discussion and authors' reply
• Regularized multitask learning for multidimensional log-density gradient estimation
• Multivariate log-concave distributions as a nearly parametric model
• A computational approach to log-concave density estimation
• Shape Constrained Kernel PDF and PMF Estimation
• Assessing log-concavity of multivariate densities
• Density estimation for shift-invariant multidimensional distributions

Describes a project that uses

Uses Software

• fmlogcondens
• LogConcDEAD
• Qhull
• CRAN
• R
• mclust

This page was built for publication: Fast multivariate log-concave density estimation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2337320)