Robust and Efficient Approximate Bayesian Computation: A Minimum Distance Approach
Start Date
June 11, 2020
End Date
June 11, 2020
Registration
Closed
AMSI Advanced Collaborative Environment (ACE) seminar
Statistics and Stochastic colloquium
(part of the Colloquium Series of the Department of Mathematics and Statistics) at La Trobe University.
Date: 11 June 2020 12:00pm–1:30pm (AEST)
Speaker: Dr David Frazier, Monash University
Title: Robust and Efficient Approximate Bayesian Computation: A Minimum Distance Approach
Zoom/Website: https://latrobe.zoom.us/j/98357628534
Abstract
In many instances, the application of approximate Bayesian methods is hampered by two practical features:
- the requirement to project the data down to low-dimensional summary, including the choice of this projection, and which ultimately yields inefficient inference;
- a possible lack of robustness of these methods to deviations from the underlying model structure.
Motivated by these efficiency and robustness concerns, we construct a new Bayesian method that can deliver efficient estimators when the underlying model is well-specified, and which is simultaneously robust to certain forms of model misspecification. This new approach bypasses the calculation of summaries by considering a norm between empirical and simulated probability measures. For specific choices of the norm, we demonstrate that this approach can be as efficient as exact Bayesian inference, and is robust to deviations from the underlying model assumptions. We illustrate this approach using several examples that have featured in the literature.
Related Event
Show All
International Congress of Mathematicians (ICM) 2026
July 23, 2026
MATRIX Program: Slow Viscous Flows with Interfaces
July 17, 2025
MISG 2025
February 10, 2025
ANZIAM 2025
February 2, 2025