Deep Optimal Sensor Placement for Black Box Stochastic Simulations
This addresses computational barriers in sensor placement for stochastic simulations, offering a more efficient solution for researchers and engineers in fields like environmental monitoring or industrial systems.
The paper tackles the problem of selecting optimal sensor configurations for parameter inference in black-box stochastic systems by proposing a novel approach that models the joint distribution with an energy-based model trained on simulation data. The method provides highly informative sensor locations at lower computational cost compared to conventional approaches.
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.