Deep Optimal Sensor Placement for Black Box Stochastic Simulations

TL;DR

This paper introduces a novel energy-based model for optimal sensor placement in black-box stochastic systems, enabling efficient, flexible, and cost-effective inference of parameters across diverse problems.

Contribution

It presents a joint energy-based modeling approach that is resolution-independent and adaptable for sensor placement, improving over existing methods in efficiency and flexibility.

Findings

Provides highly informative sensor locations

Reduces computational cost compared to traditional methods

Validates effectiveness across various stochastic problems

Abstract

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.