Bayesian fractional posteriors

Anirban Bhattacharya, Debdeep Pati, And Y.U.N. Yang

Research output: Contribution to journalArticlepeer-review


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.

Original languageEnglish (US)
Pages (from-to)39-66
Number of pages28
JournalAnnals of Statistics
Issue number1
StatePublished - Feb 2019


  • Convex regression
  • Misspecified models
  • Oracle inequality
  • PAC-Bayes
  • Posterior contraction
  • Rényi divergence

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty


Dive into the research topics of 'Bayesian fractional posteriors'. Together they form a unique fingerprint.

Cite this