Saved in:
Bibliographic Details
Main Authors: Cui, Jingkai, Qin, Qian
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.20041
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917165707296768
author Cui, Jingkai
Qin, Qian
author_facet Cui, Jingkai
Qin, Qian
contents We study the convergence properties of a class of data augmentation algorithms targeting posterior distributions of Bayesian lasso models with log-concave likelihoods. Leveraging isoperimetric inequalities, we derive a generic convergence bound for this class of algorithms and apply it to Bayesian probit, logistic, and heteroskedastic Gaussian linear lasso models. Under feasible initializations, the mixing times for the probit and logistic models are of order $O[(p+n)^3 (pn^{1-c} + n)]$, up to logarithmic factors, where $n$ is the sample size, $p$ is the dimension of the regression coefficients, and $c \in [0,1]$ is determined by the lasso penalty parameter. The mixing time for the heteroskedastic Gaussian model is $O[n(n+p)^3 (p n^{1-c} + n)]$, up to logarithmic factors.
format Preprint
id arxiv_https___arxiv_org_abs_2512_20041
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Convergence analysis of data augmentation algorithms in Bayesian lasso models with log-concave likelihoods
Cui, Jingkai
Qin, Qian
Statistics Theory
60J05
We study the convergence properties of a class of data augmentation algorithms targeting posterior distributions of Bayesian lasso models with log-concave likelihoods. Leveraging isoperimetric inequalities, we derive a generic convergence bound for this class of algorithms and apply it to Bayesian probit, logistic, and heteroskedastic Gaussian linear lasso models. Under feasible initializations, the mixing times for the probit and logistic models are of order $O[(p+n)^3 (pn^{1-c} + n)]$, up to logarithmic factors, where $n$ is the sample size, $p$ is the dimension of the regression coefficients, and $c \in [0,1]$ is determined by the lasso penalty parameter. The mixing time for the heteroskedastic Gaussian model is $O[n(n+p)^3 (p n^{1-c} + n)]$, up to logarithmic factors.
title Convergence analysis of data augmentation algorithms in Bayesian lasso models with log-concave likelihoods
topic Statistics Theory
60J05
url https://arxiv.org/abs/2512.20041