Scalable Semi-Modular Inference with Variational Meta-Posteriors
Carmona, Chris U., Nicholls, Geoff K.
The Cut posterior and related Semi-Modular Inference are Generalised Bayes methods for Modular Bayesian evidence combination. Analysis is broken up over modular sub-models of the joint posterior distribution. Model-misspecification in multi-modular models can be hard to fix by model elaboration alone and the Cut posterior and SMI offer a way round this. Information entering the analysis from misspecified modules is controlled by an influence parameter $\eta$ related to the learning rate. This paper contains two substantial new methods. First, we give variational methods for approximating the Cut and SMI posteriors which are adapted to the inferential goals of evidence combination. We parameterise a family of variational posteriors using a Normalising Flow for accurate approximation and end-to-end training. Secondly, we show that analysis of models with multiple cuts is feasible using a new Variational Meta-Posterior. This approximates a family of SMI posteriors indexed by $\eta$ using a single set of variational parameters.
Apr-1-2022
- Country:
- North America
- Mexico (0.04)
- United States
- New York > New York County
- New York City (0.04)
- Massachusetts > Middlesex County
- Cambridge (0.04)
- New York > New York County
- Europe
- Central Europe (0.04)
- United Kingdom > England
- Oxfordshire > Oxford (0.14)
- Iceland > Capital Region
- Reykjavik (0.04)
- France > Hauts-de-France
- Asia
- Middle East > Jordan (0.04)
- Bangladesh > Dhaka Division
- Dhaka District > Dhaka (0.04)
- North America
- Genre:
- Research Report (0.83)
- Industry:
- Health & Medicine
- Epidemiology (0.92)
- Therapeutic Area (0.67)
- Health & Medicine