Nonparametric predictive inference for discrete data via Metropolis-adjusted Dirichlet sequences

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Agnoletto, Davide, Rigon, Tommaso, Dunson, David B.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912700462792704
author Agnoletto, Davide
Rigon, Tommaso
Dunson, David B.
author_facet Agnoletto, Davide
Rigon, Tommaso
Dunson, David B.
contents This article is motivated by challenges in conducting Bayesian inferences on unknown discrete distributions, with a particular focus on count data. To avoid the computational disadvantages of traditional mixture models, we develop a novel Bayesian predictive approach. In particular, our Metropolis-adjusted Dirichlet (MAD) sequence model characterizes the predictive measure as a mixture of a base measure and Metropolis-Hastings kernels centered on previous data points. The resulting MAD sequence is asymptotically exchangeable and the posterior on the data generator takes the form of a martingale posterior. This structure leads to straightforward algorithms for inference on count distributions, with easy extensions to multivariate, regression, and binary data cases. We obtain a useful asymptotic Gaussian approximation and illustrate the methodology on a variety of applications.
format Preprint
id arxiv_https___arxiv_org_abs_2507_08629
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Nonparametric predictive inference for discrete data via Metropolis-adjusted Dirichlet sequences
Agnoletto, Davide
Rigon, Tommaso
Dunson, David B.
Methodology
This article is motivated by challenges in conducting Bayesian inferences on unknown discrete distributions, with a particular focus on count data. To avoid the computational disadvantages of traditional mixture models, we develop a novel Bayesian predictive approach. In particular, our Metropolis-adjusted Dirichlet (MAD) sequence model characterizes the predictive measure as a mixture of a base measure and Metropolis-Hastings kernels centered on previous data points. The resulting MAD sequence is asymptotically exchangeable and the posterior on the data generator takes the form of a martingale posterior. This structure leads to straightforward algorithms for inference on count distributions, with easy extensions to multivariate, regression, and binary data cases. We obtain a useful asymptotic Gaussian approximation and illustrate the methodology on a variety of applications.
title Nonparametric predictive inference for discrete data via Metropolis-adjusted Dirichlet sequences
topic Methodology
url https://arxiv.org/abs/2507.08629