Statistics Seminars
MAP estimators and posterior consistency for Bayesian inverse problems with exponential priors
With Masoumeh Dashti, University of Sussex
MAP estimators and posterior consistency for Bayesian inverse problems with exponential priors
We consider the problem of recovering an unknown function from noisy and indirect observations. We adopt a Bayesian approach and consider a class of product exponential priors with tails between Gaussian and Laplace. We discuss some results on characterisation of the modes of the posterior measure which lead to some weak consistency results. We then show a contraction theory for the posterior measure.
This is based on joint works with S. Agapiou, M. Burger and T. Helin.
- Speaker: Masoumeh Dashti, University of Sussex
- Friday 24 May 2019, 16:00–17:00
- Venue: MR12.
- Series: Statistics; organiser: Dr Sergio Bacallado.
