Saved in:
Bibliographic Details
Main Authors: Marusic, Juraj, Medina, Marco Avella, Rush, Cynthia
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.01358
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915530498113536
author Marusic, Juraj
Medina, Marco Avella
Rush, Cynthia
author_facet Marusic, Juraj
Medina, Marco Avella
Rush, Cynthia
contents We provide a theoretical framework for a wide class of generalized posteriors that can be viewed as the natural Bayesian posterior counterpart of the class of M-estimators in the frequentist world. We call the members of this class M-posteriors and show that they are asymptotically normally distributed under mild conditions on the M-estimation loss and the prior. In particular, an M-posterior contracts in probability around a normal distribution centered at an M-estimator, showing frequentist consistency and suggesting some degree of robustness depending on the reference M-estimator. We formalize the robustness properties of the M-posteriors by a new characterization of the posterior influence function and a novel definition of breakdown point adapted for posterior distributions. We illustrate the wide applicability of our theory in various popular models and illustrate their empirical relevance in some numerical examples.
format Preprint
id arxiv_https___arxiv_org_abs_2510_01358
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A theoretical framework for M-posteriors: frequentist guarantees and robustness properties
Marusic, Juraj
Medina, Marco Avella
Rush, Cynthia
Statistics Theory
Machine Learning
We provide a theoretical framework for a wide class of generalized posteriors that can be viewed as the natural Bayesian posterior counterpart of the class of M-estimators in the frequentist world. We call the members of this class M-posteriors and show that they are asymptotically normally distributed under mild conditions on the M-estimation loss and the prior. In particular, an M-posterior contracts in probability around a normal distribution centered at an M-estimator, showing frequentist consistency and suggesting some degree of robustness depending on the reference M-estimator. We formalize the robustness properties of the M-posteriors by a new characterization of the posterior influence function and a novel definition of breakdown point adapted for posterior distributions. We illustrate the wide applicability of our theory in various popular models and illustrate their empirical relevance in some numerical examples.
title A theoretical framework for M-posteriors: frequentist guarantees and robustness properties
topic Statistics Theory
Machine Learning
url https://arxiv.org/abs/2510.01358