Guardado en:
Detalles Bibliográficos
Autores principales: Taylor, Ian, Mueller, Juliane, Bessac, Julie
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2509.21711
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911674687029248
author Taylor, Ian
Mueller, Juliane
Bessac, Julie
author_facet Taylor, Ian
Mueller, Juliane
Bessac, Julie
contents As data collection and simulation capabilities advance, multi-modal learning, the task of learning from multiple modalities and sources of data, is becoming an increasingly important area of research. Surrogate models that learn from data of multiple auxiliary modalities to support the modeling of a highly expensive quantity of interest have the potential to aid outer loop applications such as optimization, inverse problems, or sensitivity analyses when multi-modal data are available. We develop two multi-modal Bayesian neural network surrogate models and leverage conditionally conjugate distributions in the last layer to estimate model parameters using stochastic variational inference (SVI). We provide a method to perform this conjugate SVI estimation in the presence of partially missing observations. We demonstrate improved prediction accuracy and uncertainty quantification compared to uni-modal surrogate models for both scalar and time series data.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21711
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-modal Bayesian Neural Network Surrogates with Conjugate Last-Layer Estimation
Taylor, Ian
Mueller, Juliane
Bessac, Julie
Machine Learning
As data collection and simulation capabilities advance, multi-modal learning, the task of learning from multiple modalities and sources of data, is becoming an increasingly important area of research. Surrogate models that learn from data of multiple auxiliary modalities to support the modeling of a highly expensive quantity of interest have the potential to aid outer loop applications such as optimization, inverse problems, or sensitivity analyses when multi-modal data are available. We develop two multi-modal Bayesian neural network surrogate models and leverage conditionally conjugate distributions in the last layer to estimate model parameters using stochastic variational inference (SVI). We provide a method to perform this conjugate SVI estimation in the presence of partially missing observations. We demonstrate improved prediction accuracy and uncertainty quantification compared to uni-modal surrogate models for both scalar and time series data.
title Multi-modal Bayesian Neural Network Surrogates with Conjugate Last-Layer Estimation
topic Machine Learning
url https://arxiv.org/abs/2509.21711