Variational Inference over Non-differentiable Cardiac Simulators using Bayesian Optimization
This addresses the challenge of parameter inference in cardiac simulators for medical applications, but it appears incremental as it builds on existing likelihood-free methods.
The authors tackled the problem of inferring parameters for a cardiac simulator, which is intractable due to runtime constraints, by developing a likelihood-free inference method. They improved the fit of a state-of-the-art simulator to a real patient's electrocardiogram (ECG), though no concrete numbers are provided.
Performing inference over simulators is generally intractable as their runtime means we cannot compute a marginal likelihood. We develop a likelihood-free inference method to infer parameters for a cardiac simulator, which replicates electrical flow through the heart to the body surface. We improve the fit of a state-of-the-art simulator to an electrocardiogram (ECG) recorded from a real patient.