skip to content
 

Statistical guarantees for Bayesian uncertainty quantification in inverse problems

Presented by: 
Richard Nickl University of Cambridge
Date: 
Monday 9th April 2018 - 14:30 to 15:00
Venue: 
INI Seminar Room 1
Abstract: 

We discuss recent results in mathematical statistics that provide objective statistical guarantees for Bayesian algorithms in (possibly non-linear) noisy inverse problems. We focus in particular on the justification of Bayesian credible sets as proper frequentist confidence sets in the small noise limit via so-called `Bernstein - von Mises theorems', which provide Gaussian approximations to the posterior distribution, and introduce notions of such theorems in the infinite-dimensional settings relevant for inverse problems. We discuss in detail such a Bernstein-von Mises result for Bayesian inference on the unknown potential in the Schroedinger equation from an observation of the solution of that PDE corrupted by additive Gaussian white noise. See https://arxiv.org/abs/1707.01764 and also https://arxiv.org/abs/1708.06332

The video for this talk should appear here if JavaScript is enabled.
If it doesn't, something may have gone wrong with our embedded player.
We'll get it fixed as soon as possible.
Presentation Material: 
University of Cambridge Research Councils UK
    Clay Mathematics Institute London Mathematical Society NM Rothschild and Sons