Merging Rate of Opinions via Optimal Transport on Random Measures

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Catalano, Marta, Lavenant, Hugo
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912589197344768
author Catalano, Marta
Lavenant, Hugo
author_facet Catalano, Marta
Lavenant, Hugo
contents Random measures provide flexible parameters for Bayesian nonparametric models. Given two different priors for a random measure, we develop a natural framework to investigate the rate at which the corresponding posteriors merge, as the sample size increases. We define a new distance between the laws of random measures that is built as a Wasserstein distance on the ground space of unbalanced measures, endowed with the bounded Lipschitz metric. We develop tight analytical bounds for its specification to completely random measures, including the special case of Poisson and gamma random measures. The bounds are interpreted in terms of an adapted extended Wasserstein distance between the Lévy measures and are used to investigate the merging between the posteriors of normalized gamma and generalized gamma priors. After a careful study on the identifiability of the law of the random measure, interesting asymptotic and finite-sample insights are derived without putting any assumption on the true data generating process.
format Preprint
id arxiv_https___arxiv_org_abs_2305_06116
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Merging Rate of Opinions via Optimal Transport on Random Measures
Catalano, Marta
Lavenant, Hugo
Statistics Theory
Probability
60G55, 60G57, 49Q22, 62C10
Random measures provide flexible parameters for Bayesian nonparametric models. Given two different priors for a random measure, we develop a natural framework to investigate the rate at which the corresponding posteriors merge, as the sample size increases. We define a new distance between the laws of random measures that is built as a Wasserstein distance on the ground space of unbalanced measures, endowed with the bounded Lipschitz metric. We develop tight analytical bounds for its specification to completely random measures, including the special case of Poisson and gamma random measures. The bounds are interpreted in terms of an adapted extended Wasserstein distance between the Lévy measures and are used to investigate the merging between the posteriors of normalized gamma and generalized gamma priors. After a careful study on the identifiability of the law of the random measure, interesting asymptotic and finite-sample insights are derived without putting any assumption on the true data generating process.
title Merging Rate of Opinions via Optimal Transport on Random Measures
topic Statistics Theory
Probability
60G55, 60G57, 49Q22, 62C10
url https://arxiv.org/abs/2305.06116