Validation Diagnostics for SBI algorithms based on Normalizing Flows
This work addresses a critical gap in validating SBI algorithms for experimental scientists, though it is incremental as it builds on existing NF methods.
The paper tackles the lack of validation methods for simulation-based inference algorithms using Normalizing Flows, proposing interpretable diagnostics with theoretical guarantees for multi-dimensional conditional density estimation, illustrated with a challenging computational neuroscience example.
Building on the recent trend of new deep generative models known as Normalizing Flows (NF), simulation-based inference (SBI) algorithms can now efficiently accommodate arbitrary complex and high-dimensional data distributions. The development of appropriate validation methods however has fallen behind. Indeed, most of the existing metrics either require access to the true posterior distribution, or fail to provide theoretical guarantees on the consistency of the inferred approximation beyond the one-dimensional setting. This work proposes easy to interpret validation diagnostics for multi-dimensional conditional (posterior) density estimators based on NF. It also offers theoretical guarantees based on results of local consistency. The proposed workflow can be used to check, analyse and guarantee consistent behavior of the estimator. The method is illustrated with a challenging example that involves tightly coupled parameters in the context of computational neuroscience. This work should help the design of better specified models or drive the development of novel SBI-algorithms, hence allowing to build up trust on their ability to address important questions in experimental science.