Validation Diagnostics for SBI algorithms based on Normalizing Flows - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

Validation Diagnostics for SBI algorithms based on Normalizing Flows

Abstract

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.
Fichier principal
Vignette du fichier
NeurIPS_ML4PS_2022_ValDiagsSBI_arXivVersion.pdf (807.95 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03856444 , version 1 (16-11-2022)
hal-03856444 , version 2 (24-11-2022)

Licence

Attribution

Identifiers

  • HAL Id : hal-03856444 , version 2

Cite

Julia Linhart, Alexandre Gramfort, Pedro Luiz Coelho Rodrigues. Validation Diagnostics for SBI algorithms based on Normalizing Flows. NeurIPS 2022 - the 36th conference on Neural Information Processing Systems - Machine Learning and the Physical Sciences workshop, Nov 2022, New Orleans, United States. pp.1-7. ⟨hal-03856444v2⟩
85 View
34 Download

Share

Gmail Facebook X LinkedIn More