Upper and lower bounds for local Lipschitz stability of Bayesian posteriors

TL;DR

This paper investigates the sensitivity of Bayesian posteriors to perturbations, establishing bounds that depend on the evidence and showing how increased concentration affects stability.

Contribution

It provides both upper and lower bounds for the Lipschitz stability of Bayesian posteriors, emphasizing the role of evidence and concentration in sensitivity analysis.

Findings

Sensitivity increases as evidence decreases to zero.

Explicit bounds depend on the evidence.

Conditions for local bi-Lipschitz continuity are identified.

Abstract

The work of Sprungk (Inverse Problems, 2020) established the local Lipschitz continuity of the misfit-to-posterior and prior-to-posterior maps with respect to the Kullback--Leibler divergence and the total variation, Hellinger, and 1-Wasserstein metrics, by proving certain upper bounds. The upper bounds were also used to show that if a posterior measure is more concentrated, then it can be more sensitive to perturbations in the misfit or prior. We prove upper bounds and lower bounds that emphasise the importance of the evidence. The lower bounds show that the sensitivity of posteriors to perturbations in the misfit or the prior not only can increase, but in general will increase as the posterior measure becomes more concentrated, i.e. as the evidence decreases to zero. Using the explicit dependence of our bounds on the evidence, we identify sufficient conditions for the misfit-to-posterior and prior-to-posterior maps to be locally bi-Lipschitz continuous.