Deep Optimal Sensor Placement for Black Box Stochastic Simulations

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Cordero-Encinar, Paula, Schröder, Tobias, Yatsyshin, Peter, Duncan, Andrew
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917941862203392
author Cordero-Encinar, Paula
Schröder, Tobias
Yatsyshin, Peter
Duncan, Andrew
author_facet Cordero-Encinar, Paula
Schröder, Tobias
Yatsyshin, Peter
Duncan, Andrew
contents Selecting cost-effective optimal sensor configurations for subsequent inference of parameters in black-box stochastic systems faces significant computational barriers. We propose a novel and robust approach, modelling the joint distribution over input parameters and solution with a joint energy-based model, trained on simulation data. Unlike existing simulation-based inference approaches, which must be tied to a specific set of point evaluations, we learn a functional representation of parameters and solution. This is used as a resolution-independent plug-and-play surrogate for the joint distribution, which can be conditioned over any set of points, permitting an efficient approach to sensor placement. We demonstrate the validity of our framework on a variety of stochastic problems, showing that our method provides highly informative sensor locations at a lower computational cost compared to conventional approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12036
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep Optimal Sensor Placement for Black Box Stochastic Simulations
Cordero-Encinar, Paula
Schröder, Tobias
Yatsyshin, Peter
Duncan, Andrew
Machine Learning
Applications
Selecting cost-effective optimal sensor configurations for subsequent inference of parameters in black-box stochastic systems faces significant computational barriers. We propose a novel and robust approach, modelling the joint distribution over input parameters and solution with a joint energy-based model, trained on simulation data. Unlike existing simulation-based inference approaches, which must be tied to a specific set of point evaluations, we learn a functional representation of parameters and solution. This is used as a resolution-independent plug-and-play surrogate for the joint distribution, which can be conditioned over any set of points, permitting an efficient approach to sensor placement. We demonstrate the validity of our framework on a variety of stochastic problems, showing that our method provides highly informative sensor locations at a lower computational cost compared to conventional approaches.
title Deep Optimal Sensor Placement for Black Box Stochastic Simulations
topic Machine Learning
Applications
url https://arxiv.org/abs/2410.12036