Approximate Bayesian Computation with Deep Learning and Conformal prediction - INRAE - Institut national de recherche pour l’agriculture, l’alimentation et l’environnement Access content directly
Preprints, Working Papers, ... Year : 2024

Approximate Bayesian Computation with Deep Learning and Conformal prediction


Approximate Bayesian Computation (ABC) methods are commonly used to approximate posterior distributions in models with unknown or computationally intractable likelihoods. Classical ABC methods are based on nearest neighbor type algorithms and rely on the choice of so-called summary statistics, distances between datasets and a tolerance threshold. Recently, methods combining ABC with more complex machine learning algorithms have been proposed to mitigate the impact of these "user-choices". In this paper, we propose the first, to our knowledge, ABC method completely free of summary statistics, distance and tolerance threshold. Moreover, in contrast with usual generalizations of the ABC method, it associates a confidence interval (having a proper frequentist marginal coverage) with the posterior mean estimation (or other moment-type estimates). Our method, ABCD-Conformal, uses a neural network with Monte Carlo Dropout to provide an estimation of the posterior mean (or others moment type functional), and conformal theory to obtain associated confidence sets. Efficient for estimating multidimensional parameters, we test this new method on three different applications and compare it with other ABC methods in the literature.
Fichier principal
Vignette du fichier
2024-05-31_ABCDconformal_HAL.pdf (1.29 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04595814 , version 1 (03-06-2024)
hal-04595814 , version 2 (09-07-2024)


  • HAL Id : hal-04595814 , version 1


Meïli Baragatti, Bertrand Cloez, David Métivier, Isabelle Sanchez. Approximate Bayesian Computation with Deep Learning and Conformal prediction. 2024. ⟨hal-04595814v1⟩


20 View
4 Download


Gmail Mastodon Facebook X LinkedIn More