Variational Transdimensional Inference

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Davies, Laurence, Mackinlay, Dan, Oliveira, Rafael, Sisson, Scott A.
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915798947201024
author Davies, Laurence
Mackinlay, Dan
Oliveira, Rafael
Sisson, Scott A.
author_facet Davies, Laurence
Mackinlay, Dan
Oliveira, Rafael
Sisson, Scott A.
contents The expressiveness of flow-based models combined with stochastic variational inference (SVI) has expanded the application of optimization-based Bayesian inference to highly complex problems. However, despite the importance of multi-model Bayesian inference for problems defined on a transdimensional joint model and parameter space, such as Bayesian structure learning and model selection, flow-based SVI has been limited to problems defined on a fixed-dimensional parameter space. We introduce CoSMIC, normalizing flows (COntextually-Specified Masking for Identity-mapped Components), an extension to neural autoregressive conditional normalizing flow architectures that enables use of a single flow-based variational density for inference over a transdimensional (multi-model) conditional target distribution. We propose a combined stochastic variational transdimensional inference (VTI) approach to training CoSMIC, flows using ideas from Bayesian optimization and Monte Carlo gradient estimation. Numerical experiments show the performance of VTI on challenging problems that scale to high-cardinality model spaces.
format Preprint
id arxiv_https___arxiv_org_abs_2506_04749
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Variational Transdimensional Inference
Davies, Laurence
Mackinlay, Dan
Oliveira, Rafael
Sisson, Scott A.
Computation
Methodology
Machine Learning
The expressiveness of flow-based models combined with stochastic variational inference (SVI) has expanded the application of optimization-based Bayesian inference to highly complex problems. However, despite the importance of multi-model Bayesian inference for problems defined on a transdimensional joint model and parameter space, such as Bayesian structure learning and model selection, flow-based SVI has been limited to problems defined on a fixed-dimensional parameter space. We introduce CoSMIC, normalizing flows (COntextually-Specified Masking for Identity-mapped Components), an extension to neural autoregressive conditional normalizing flow architectures that enables use of a single flow-based variational density for inference over a transdimensional (multi-model) conditional target distribution. We propose a combined stochastic variational transdimensional inference (VTI) approach to training CoSMIC, flows using ideas from Bayesian optimization and Monte Carlo gradient estimation. Numerical experiments show the performance of VTI on challenging problems that scale to high-cardinality model spaces.
title Variational Transdimensional Inference
topic Computation
Methodology
Machine Learning
url https://arxiv.org/abs/2506.04749