Bayesian fractional posteriors
Academic Article
-
- Overview
-
- Research
-
- Identity
-
- Additional Document Info
-
- View All
-
Overview
abstract
-
© Institute of Mathematical Statistics, 2019. We consider the fractional posterior distribution that is obtained by updating a prior distribution via Bayes theorem with a fractional likelihood function, a usual likelihood function raised to a fractional power. First, we analyze the contraction property of the fractional posterior in a general misspecified framework. Our contraction results only require a prior mass condition on certain Kullback–Leibler (KL) neighborhood of the true parameter (or the KL divergence minimizer in the misspecified case), and obviate constructions of test functions and sieves commonly used in the literature for analyzing the contraction property of a regular posterior. We show through a counterexample that some condition controlling the complexity of the parameter space is necessary for the regular posterior to contract, rendering additional flexibility on the choice of the prior for the fractional posterior. Second, we derive a novel Bayesian oracle inequality based on a PAC-Bayes inequality in misspecified models. Our derivation reveals several advantages of averaging based Bayesian procedures over optimization based frequentist procedures. As an application of the Bayesian oracle inequality, we derive a sharp oracle inequality in multivariate convex regression problems. We also illustrate the theory in Gaussian process regression and density estimation problems.
published proceedings
altmetric score
author list (cited authors)
-
Bhattacharya, A., Pati, D., & Yang, Y.
citation count
complete list of authors
-
Bhattacharya, Anirban||Pati, Debdeep||Yang, Yun
publication date
publisher
published in
Research
keywords
-
Convex Regression
-
Generic Health Relevance
-
Misspecified Models
-
Oracle Inequality
-
Pac-bayes
-
Posterior Contraction
-
Renyi Divergence
Identity
Digital Object Identifier (DOI)
Additional Document Info
start page
end page
volume
issue