Easy High-Dimensional Likelihood-Free Inference
This work addresses challenges in statistical inference for researchers dealing with complex models, though it appears incremental as it builds on existing GAN and LFI methods.
The paper tackles the problem of likelihood-free inference and Approximate Bayesian Computation by introducing a framework that uses Generative Adversarial Networks to replace black-box simulators and generate summary features, resulting in improved scalability and ability to handle high-dimensional data and complex distributions on benchmark datasets.
We introduce a framework using Generative Adversarial Networks (GANs) for likelihood--free inference (LFI) and Approximate Bayesian Computation (ABC) where we replace the black-box simulator model with an approximator network and generate a rich set of summary features in a data driven fashion. On benchmark data sets, our approach improves on others with respect to scalability, ability to handle high dimensional data and complex probability distributions.