Corpus ID: 88523397

Variational Inference over Non-differentiable Cardiac Simulators using Bayesian Optimization

@article{McCarthy2017VariationalIO,
  title={Variational Inference over Non-differentiable Cardiac Simulators using Bayesian Optimization},
  author={Adam McCarthy and B. Rodr{\'i}guez and A. Minchol{\'e}},
  journal={arXiv: Machine Learning},
  year={2017}
}
  • Adam McCarthy, B. Rodríguez, A. Mincholé
  • Published 2017
  • Mathematics
  • arXiv: Machine Learning
  • 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. 
    4 Citations

    Figures from this paper.

    Automatic Posterior Transformation for Likelihood-Free Inference
    • 35
    • PDF
    Adversarial Variational Optimization of Non-Differentiable Simulators
    • 40
    • PDF
    Strategic Plan for a Scientific Software Innovation Institute (S2I2) for High Energy Physics
    • 5
    • PDF

    References

    SHOWING 1-10 OF 30 REFERENCES
    Operator Variational Inference
    • 87
    • PDF
    GPS-ABC: Gaussian Process Surrogate Approximate Bayesian Computation
    • 90
    • PDF
    Fast ε-free Inference of Simulation Models with Bayesian Conditional Density Estimation
    • 91
    • PDF
    Adversarial Variational Optimization of Non-Differentiable Simulators
    • 40
    • PDF
    Black Box Variational Inference
    • 634
    • PDF
    Auto-Encoding Variational Bayes
    • 9,710
    • Highly Influential
    • PDF
    Markov chain Monte Carlo without likelihoods
    • 1,046
    • PDF
    Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inference
    • 85
    • PDF