ADAVI: Automatic Dual Amortized Variational Inference Applied To Pyramidal Bayesian Models - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

ADAVI: Automatic Dual Amortized Variational Inference Applied To Pyramidal Bayesian Models

Abstract

Frequently, population studies feature pyramidally-organized data represented using Hierarchical Bayesian Models (HBM) enriched with plates. These models can become prohibitively large in settings such as neuroimaging, where a sample is composed of a functional MRI signal measured on 300 brain locations, across 4 measurement sessions, and 30 subjects, resulting in around 1 million latent parameters. Such high dimensionality hampers the usage of modern, expressive flow-based techniques. To infer parameter posterior distributions in this challenging class of problems, we designed a novel methodology that automatically produces a variational family dual to a target HBM. This variational family, represented as a neural network, consists in the combination of an attention-based hierarchical encoder feeding summary statistics to a set of normalizing flows. Our automatically-derived neural network exploits exchangeability in the plate-enriched HBM and factorizes its parameter space. The resulting architecture reduces by orders of magnitude its parameterization with respect to that of a typical flow-based representation, while maintaining expressivity. Our method performs inference on the specified HBM in an amortized setup: once trained, it can readily be applied to a new data sample to compute the parameters' full posterior. We demonstrate the capability and scalability of our method on simulated data, as well as a challenging high-dimensional brain parcellation experiment. We also open up several questions that lie at the intersection between normalizing flows, SBI, structured Variational Inference, and inference amortization.
Fichier principal
Vignette du fichier
ADAVI_ICLR2022.pdf (2.48 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03267956 , version 1 (23-06-2021)
hal-03267956 , version 2 (12-10-2021)
hal-03267956 , version 3 (14-10-2021)
hal-03267956 , version 4 (07-03-2022)

Identifiers

Cite

Louis Rouillard, Demian Wassermann. ADAVI: Automatic Dual Amortized Variational Inference Applied To Pyramidal Bayesian Models. ICLR 2022, Apr 2022, Virtual, France. ⟨10.48550/arXiv.2106.12248⟩. ⟨hal-03267956v4⟩
192 View
212 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More