The ABC of Simulation-Based Inference

Henrik Häggström

Thu Sep 17, 14:30-15:00 (2 weeks ago)

Abstract: Many scientific models are easy to simulate but have likelihoods that are difficult or even impossible to evaluate. Simulation-based inference lets us perform Bayesian inference in these situations using simulations instead. In this seminar, I will introduce the main ideas through Approximate Bayesian Computation (ABC), before discussing some practical challenges and more modern approaches.

Mathematics

Audience: general audience


Gothenburg PhD seminar

Series comments: Rooms and times may vary, please check the latest update. In-person only.

Organizers: Anna Theorin Johansson*, Lotta Eriksson*
*contact for this listing

Export talk to