Bayesian constraint relaxation

DOI10.1093/BIOMET/ASZ069zbMATH Open1435.62382arXiv1801.01525OpenAlexW2997363127WikidataQ89848429 ScholiaQ89848429MaRDI QIDQ5222228FDOQ5222228

Authors: Leo L. Duan, Alexander L. Young, Akihiko Nishimura, David Dunson 

Publication date: 1 April 2020

Published in: Biometrika (Search for Journal in Brave)

Abstract: Prior information often takes the form of parameter constraints. Bayesian methods include such information through prior distributions having constrained support. By using posterior sampling algorithms, one can quantify uncertainty without relying on asymptotic approximations. However, sharply constrained priors are (a) not necessary in some settings; and (b) tend to limit modeling scope to a narrow set of distributions that are tractable computationally. Inspired by the vast literature that replaces the slab-and-spike prior with a continuous approximation, we propose to replace the sharp indicator function of the constraint with an exponential kernel, thereby creating a close-to-constrained neighborhood within the Euclidean space in which the constrained subspace is embedded. This kernel decays with distance from the constrained space at a rate depending on a relaxation hyperparameter. By avoiding the sharp constraint, we enable use of off-the-shelf posterior sampling algorithms, such as Hamiltonian Monte Carlo, facilitating automatic computation in broad models. We study the constrained and relaxed distributions under multiple settings, and theoretically quantify their differences. We illustrate the method through multiple novel modeling examples.

Full work available at URL: https://arxiv.org/abs/1801.01525

Recommendations

• Bayesian regression under combinations of constraints
• Efficient Bayesian shape-restricted function estimation with constrained Gaussian process priors
• Monte Carlo methods for Bayesian analysis of constrained parameter problems
• On Bayesian estimation of regression models subject to uncertainty about functional constraints
• Sequentially constrained Monte Carlo

zbMATH Keywords

factor modelshrinkageparameter restrictionconstrained Bayesorthonormalitymanifold constraintconstraint functionordered simplex

Mathematics Subject Classification ID

Bayesian inference (62F15) Applications of statistics to biology and medical sciences; meta analysis (62P10) Statistics on manifolds (62R30)

Cited In (7)

• A Mass-Shifting Phenomenon of Truncated Multivariate Normal Priors
• Discussions
• Sampling constrained probability distributions using spherical augmentation
• Sequentially constrained Monte Carlo
• Bayesian singular value regularization via a cumulative shrinkage process
• Inference about constrained parameters using the elastic belief method
• Constraints versus priors

This page was built for publication: Bayesian constraint relaxation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5222228)