Robust neural posterior estimation and statistical model criticism
Computer simulations have proven a valuable tool for understanding complex phenomena
across the sciences. However, the utility of simulators for modelling and forecasting …
across the sciences. However, the utility of simulators for modelling and forecasting …
Robust Bayesian inference for simulator-based models via the MMD posterior bootstrap
C Dellaporta, J Knoblauch… - International …, 2022 - proceedings.mlr.press
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 …
synthetic data is possible. They are often used to describe complex real-world phenomena …
Learning robust statistics for simulation-based inference under model misspecification
Simulation-based inference (SBI) methods such as approximate Bayesian computation
(ABC), synthetic likelihood, and neural posterior estimation (NPE) rely on simulating …
(ABC), synthetic likelihood, and neural posterior estimation (NPE) rely on simulating …
Investigating the impact of model misspecification in neural simulation-based inference
Aided by advances in neural density estimation, considerable progress has been made in
recent years towards a suite of simulation-based inference (SBI) methods capable of …
recent years towards a suite of simulation-based inference (SBI) methods capable of …
Some models are useful, but how do we know which ones? Towards a unified Bayesian model taxonomy
Probabilistic (Bayesian) modeling has experienced a surge of applications in almost all
quantitative sciences and industrial areas. This development is driven by a combination of …
quantitative sciences and industrial areas. This development is driven by a combination of …
Meta-uncertainty in Bayesian model comparison
Bayesian model comparison (BMC) offers a principled probabilistic approach to study and
rank competing models. In standard BMC, we construct a discrete probability distribution …
rank competing models. In standard BMC, we construct a discrete probability distribution …
A comparison of likelihood-free methods with and without summary statistics
C Drovandi, DT Frazier - Statistics and Computing, 2022 - Springer
Likelihood-free methods are useful for parameter estimation of complex models with
intractable likelihood functions for which it is easy to simulate data. Such models are …
intractable likelihood functions for which it is easy to simulate data. Such models are …
Computed tomography and magnetic resonance imaging are potential noninvasive methods for evaluating the cisterna chyli in cats
NG Martín, ED Miño - Journal of the American Veterinary …, 2023 - Am Vet Med Assoc
OBJECTIVE There is limited information on the normal appearance of the cisterna chyli (CC)
in cats on CT and MRI. The aim of this retrospective study was to describe the CT and MRI …
in cats on CT and MRI. The aim of this retrospective study was to describe the CT and MRI …
Detecting model misspecification in amortized Bayesian inference with neural networks
Recent advances in probabilistic deep learning enable efficient amortized Bayesian
inference in settings where the likelihood function is only implicitly defined by a simulation …
inference in settings where the likelihood function is only implicitly defined by a simulation …
Misspecification-robust sequential neural likelihood
Simulation-based inference (SBI) techniques are now an essential tool for the parameter
estimation of mechanistic and simulatable models with intractable likelihoods. Statistical …
estimation of mechanistic and simulatable models with intractable likelihoods. Statistical …