Simulation-based inference with deep ensembles: evaluating calibration uncertainty and detecting model misspecification

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 ou...

Deskribapen osoa

Xehetasun bibliografikoak

Egile Nagusiak:	James Alvey, Carlo R Contaldi, Mauro Pieroni
Formatua:	Artigo
Hizkuntza:	Inglês
Argitaratua:	IOP Publishing 2026-01-01
Saila:	Machine Learning: Science and Technology
Gaiak:	simulation-based inference uncertainty quantification deep ensembles model diagnostics Bayesian inference model misspecification
Sarrera elektronikoa:	https://doi.org/10.1088/2632-2153/ae3103
Etiketak:	Etiketa erantsi Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!