Distilling Importance Sampling for Likelihood Free Inference

DOI10.1080/10618600.2023.2175688MaRDI QIDQ6141168zbMATH OpenOpenAlexFDO

Authors D. Prangle, Cecilia Viscardi

Publication date 22 January 2024

Published in Journal of Computational and Graphical Statistics (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/1910.03632

zbMATH Keywords

likelihood-free inferencenormalizing flowsepidemicsqueues

Mathematics Subject Classification ID

Statistics (62-XX)

Abstract: Likelihood-free inference involves inferring parameter values given observed data and a simulator model. The simulator is computer code which takes parameters, performs stochastic calculations, and outputs simulated data. In this work, we view the simulator as a function whose inputs are (1) the parameters and (2) a vector of pseudo-random draws. We attempt to infer all these inputs conditional on the observations. This is challenging as the resulting posterior can be high dimensional and involve strong dependence. We approximate the posterior using normalizing flows, a flexible parametric family of densities. Training data is generated by likelihood-free importance sampling with a large bandwidth value epsilon, which makes the target similar to the prior. The training data is "distilled" by using it to train an updated normalizing flow. The process is iterated, using the updated flow as the importance sampling proposal, and slowly reducing epsilon so the target becomes closer to the posterior. Unlike most other likelihood-free methods, we avoid the need to reduce data to low dimensional summary statistics, and hence can achieve more accurate results. We illustrate our method in two challenging examples, on queuing and epidemiology.

Cites work

• scientific article; zbMATH DE number 1702339 (Why is no real title available?)
• scientific article; zbMATH DE number 3150484 (Why is no real title available?)
• scientific article; zbMATH DE number 2061729 (Why is no real title available?)
• scientific article; zbMATH DE number 6982909 (Why is no real title available?)
• scientific article; zbMATH DE number 7370574 (Why is no real title available?)
• A rare event approach to high-dimensional approximate Bayesian computation
• Adaptive multiple importance sampling
• An adaptive sequential Monte Carlo method for approximate Bayesian computation
• Approximate Bayesian computational methods
• Asymptotically exact inference in differentiable generative models
• Bayesian inference of spreading processes on networks
• Estimation for an M/G/  queue with incomplete information
• Importance sampling: intrinsic dimension and computational cost
• Monte Carlo gradient estimation in machine learning
• Simulation and the Monte Carlo method
• The cross-entropy method for combinatorial and continuous optimization
• The sample size required in importance sampling
• Transport Monte Carlo: High-Accuracy Posterior Approximation via Random Transport
• Transport map accelerated adaptive importance sampling, and application to inverse problems arising from multiscale stochastic reaction networks

Cited in

(1)

• Discrete-time compartmental models with partially observed data: a comparison among frequentist and Bayesian approaches for addressing likelihood intractability

This page was built for publication: Distilling Importance Sampling for Likelihood Free Inference

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6141168)