Robust Bayesian Inference for Simulator-based Models via the MMD Posterior Bootstrap
This addresses the issue of robust Bayesian inference for complex real-world phenomena where simulators are often misspecified, offering a highly-parallelisable solution with theoretical guarantees.
The paper tackles the problem of poor performance of existing Bayesian methods for simulator-based models under misspecification, proposing a novel algorithm based on posterior bootstrap and maximum mean discrepancy that achieves strong robustness properties, as demonstrated through theoretical analysis and examples like a g-and-k distribution and toggle-switch model.
Simulator-based models are models for which the likelihood is intractable but simulation of synthetic data is possible. They are often used to describe complex real-world phenomena, and as such can often be misspecified in practice. Unfortunately, existing Bayesian approaches for simulators are known to perform poorly in those cases. In this paper, we propose a novel algorithm based on the posterior bootstrap and maximum mean discrepancy estimators. This leads to a highly-parallelisable Bayesian inference algorithm with strong robustness properties. This is demonstrated through an in-depth theoretical study which includes generalisation bounds and proofs of frequentist consistency and robustness of our posterior. The approach is then assessed on a range of examples including a g-and-k distribution and a toggle-switch model.