(AGENPARL) – VENEZIA mer 24 maggio 2023 Speaker: Cecilia Viscardi, Dipartimento di Statistica, Informatica, Applicazioni ‘G. Parenti’ (DiSIA), Università degli Studi di Firenze

The talk will also be available via Zoom https://unive.zoom.us/j/
Meeting ID: 851 5326 8624
Passcode: SanMarco2

Abstract:
Approximate Bayesian computation (ABC) is a class of methods for drawing inferences when the likelihood function is unavailable or computationally demanding to evaluate. Importance sampling and other algorithms using sequential importance sampling steps are state-of-art methods in ABC. Most of them get samples from tempered approximate posterior distributions defined by considering a decreasing sequence of ABC tolerance thresholds. Their efficiency is sensitive to the choice of an adequate proposal distribution and/or forward kernel function. We present a novel ABC method addressing this problem by combining importance sampling steps and optimization procedures. We resort to Normalising Flows (NFs) to optimize proposal distributions over a family of densities to transport particles drawn at each step towards the next tempered target. Therefore, the combination of sampling and optimization steps allows tempered distributions to get efficiently closer to the target posterior.

Results presented during this talk are from ongoing research that builds the paper
Dennis Prangle & Cecilia Viscardi (2023) Distilling Importance Sampling for Likelihood Free Inference, Journal of Computational and Graphical Statistics
DOI: https://doi.org/10.1080/.2023.

Bio Sketch:
Cecilia Viscardi is Researcher in Statistics at the Università degli studi di Firenze. He holds a PhD in Statistics from the Università degli studi di Firenze. His research focuses on the Bayesian statistics, Bayesian simulated inference, approximate Bayesian computation, Markov Chain Monte Carlo methods, epidemiological models, data anonymization.

Fonte/Source: http://www.unive.it/data/agenda/1/75035