This webinar is part of the QUT Centre for Data Science’s EC Bayes series.
Speaker: Sebastiano Grazzi, University of Warwick, UK
Abstract: In this talk, I will formally introduce piecewise deterministic Markov processes (PDMPs) endowed with “sticky floors”, “soft/hard walls” and “teleportation portals” which can be used for Monte Carlo simulation and allow to target efficiently a rich class of measures arising in Bayesian inference. I will motivate and illustrate the framework with three challenging statistical applications: Bayesian variable selection, for sampling the latent space of infection times with unknown infected population size in the SIR model with notifications and for sampling efficiently the invariant measure in hard-sphere models. The class of processes presented here extends [1] and is joint work with J. Bierkens, G. Roberts, and M. Schauer. [1] Sticky PDMP samplers for sparse and local inference problem; Bierkens J., Grazzi S., van der Maulen F., Schauer M.
Details:
| Start Date: | 02/11/2022 [add to calendar] |