BibTeX

@article{2507.13495v1,
Author        = {James Alvey and Carlo R. Contaldi and Mauro Pieroni},
Title         = {Simulation-based inference with deep ensembles: Evaluating calibration
  uncertainty and detecting model misspecification},
Eprint        = {2507.13495v1},
ArchivePrefix = {arXiv},
PrimaryClass  = {astro-ph.IM},
Abstract      = {Simulation-Based Inference (SBI) offers a principled and flexible framework
for conducting Bayesian inference in any situation where forward simulations
are feasible. However, validating the accuracy and reliability of the inferred
posteriors remains a persistent challenge. In this work, we point out a simple
diagnostic approach rooted in ensemble learning methods to assess the internal
consistency of SBI outputs that does not require access to the true posterior.
By training multiple neural estimators under identical conditions and
evaluating their pairwise Kullback-Leibler (KL) divergences, we define a
consistency criterion that quantifies agreement across the ensemble. We
highlight two core use cases for this framework: a) for generating a robust
estimate of the systematic uncertainty in parameter reconstruction associated
with the training procedure, and b) for detecting possible model
misspecification when using trained estimators on real data. We also
demonstrate the relationship between significant KL divergences and issues such
as insufficient convergence due to, e.g., too low a simulation budget, or
intrinsic variance in the training process. Overall, this ensemble-based
diagnostic framework provides a lightweight, scalable, and model-agnostic tool
for enhancing the trustworthiness of SBI in scientific applications.},
Year          = {2025},
Month         = {Jul},
Url           = {http://arxiv.org/abs/2507.13495v1},
File          = {2507.13495v1.pdf}
}