Join us this Friday, April 17th at 3pm exclusively on zoom for the next meeting of the Stats and ML Journal Club. This week, Sebastian Wagner-Carena will leed a discussion on posterior transforms for likelihood-free inference. See you then!
Abstract: How can one perform Bayesian inference on stochastic simulators with intractable likelihoods? A recent approach is to learn the posterior from adaptively proposed simulations using neural network-based conditional density estimators. However, existing methods are limited to a narrow range of proposal distributions or require importance weighting that can limit performance in practice. Here we present automatic posterior transformation (APT), a new sequential neural posterior estimation method for simulation-based inference. APT can modify the posterior estimate using arbitrary, dynamically updated proposals, and is compatible with powerful flow-based density estimators. It is more flexible, scalable and efficient than previous simulation-based inference techniques. APT can operate directly on high dimensional time series and image data, opening up new applications for likelihood-free inference.