Adaptive Bayesian nonparametric regression using a kernel mixture of polynomials with application to partial linear models
From MaRDI portal
Publication:2297237
DOI10.1214/19-BA1148zbMATH Open1437.62155arXiv1710.08017OpenAlexW2963414047WikidataQ128386708 ScholiaQ128386708MaRDI QIDQ2297237FDOQ2297237
Authors: Fangzheng Xie, Yanxun Xu 
Publication date: 18 February 2020
Published in: Bayesian Analysis (Search for Journal in Brave)
Abstract: We propose a kernel mixture of polynomials prior for Bayesian nonparametric regression. The regression function is modeled by local averages of polynomials with kernel mixture weights. We obtain the minimax-optimal rate of contraction of the full posterior distribution up to a logarithmic factor that adapts to the smoothness level of the true function by estimating metric entropies of certain function classes. We also provide a frequentist sieve maximum likelihood estimator with a near-optimal convergence rate. We further investigate the application of the kernel mixture of polynomials to the partial linear model and obtain both the near-optimal rate of contraction for the nonparametric component and the Bernstein-von Mises limit (i.e., asymptotic normality) of the parametric component. The proposed method is illustrated with numerical examples and shows superior performance in terms of computational efficiency, accuracy, and uncertainty quantification compared to the local polynomial regression, DiceKriging, and the robust Gaussian stochastic process.
Full work available at URL: https://arxiv.org/abs/1710.08017
Recommendations
- Adaptive nonparametric Bayesian inference using location-scale mixture priors
- Adaptive-modal Bayesian nonparametric regression
- Bayesian estimation for nonparametric regression
- Locally adaptive Bayes nonparametric regression via nested Gaussian processes
- Supremum norm posterior contraction and credible sets for nonparametric multivariate regression
Bayesian nonparametric regressionpartial linear modelrate of contractionmetric entropiesBernstein-von Mises limit
Nonparametric regression and quantile regression (62G08) General nonlinear regression (62J02) Gaussian processes (60G15)
Cites Work
- Bayesian data analysis.
- Title not available (Why is that?)
- Markov chain Monte Carlo methods and the label switching problem in Bayesian mixture modeling
- Gaussian processes for machine learning.
- Computational and Inferential Difficulties with Mixture Posterior Distributions
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Semiparametric least squares (SLS) and weighted SLS estimation of single-index models
- Entropies and rates of convergence for maximum likelihood and Bayes estimation for mixtures of normal densities.
- Robust Gaussian stochastic process emulation
- Anisotropic function estimation using multi-bandwidth Gaussian processes
- Root-N-Consistent Semiparametric Regression
- Title not available (Why is that?)
- Dirichlet–Laplace Priors for Optimal Shrinkage
- Fundamentals of Nonparametric Bayesian Inference
- Adaptive Bayesian estimation using a Gaussian random field with inverse gamma bandwidth
- Efficient calibration for imperfect computer models
- Convergence rates of posterior distributions for non iid observations
- Convergence rates of posterior distributions.
- Title not available (Why is that?)
- Optimal global rates of convergence for nonparametric regression
- Posterior contraction in sparse Bayesian factor models for massive covariance matrices
- Title not available (Why is that?)
- Bayesian inference for latent biologic structure with determinantal point processes (DPP)
- Bayesian estimation of sparse signals with a continuous spike-and-slab prior
- A distribution-free theory of nonparametric regression
- An Efficient Semiparametric Estimator for Binary Response Models
- Orthogonal Gaussian process models
- The semiparametric Bernstein-von Mises theorem
- Bayesian inverse problems with Gaussian priors
- Convergence rates for parametric components in a partly linear model
- Adaptive Bayesian density estimation with location-scale mixtures
- Frequentist coverage of adaptive nonparametric Bayesian credible sets
- Root-n-consistent estimation of partially linear time series models
- Adaptive Bayesian multivariate density estimation with Dirichlet mixtures
- Adaptive nonparametric Bayesian inference using location-scale mixture priors
- Rates of contraction of posterior distributions based on Gaussian process priors
- Posterior convergence rates of Dirichlet mixtures at smooth densities
- Convergence rate of sieve estimates
- Needles and straw in a haystack: posterior concentration for possibly sparse sequences
- Title not available (Why is that?)
- Adaptive estimation of multivariate functions using conditionally Gaussian tensor-product spline priors
- Supremum norm posterior contraction and credible sets for nonparametric multivariate regression
- Rate-optimal posterior contraction for sparse PCA
- Bayesian Inference for Semiparametric Regression Using a Fourier Representation
- Bayesian inference with rescaled Gaussian process priors
- A Partially Linear Model Using a Gaussian Process Prior
- Posterior concentration for Bayesian regression trees and forests
- Adaptive Bayesian nonparametric regression using a kernel mixture of polynomials with application to partial linear models
Cited In (3)
Uses Software
This page was built for publication: Adaptive Bayesian nonparametric regression using a kernel mixture of polynomials with application to partial linear models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2297237)
