FNOPE: Simulation-based inference on function spaces with Fourier Neural Operators
FNOPE: Simulation-based inference on function spaces with Fourier Neural Operators
Simulation-based inference (SBI) is an established approach for performing Bayesian inference on scientific simulators. SBI so far works best on low-dimensional parametric models. However, it is difficult to infer function-valued parameters, which frequently occur in disciplines that model spatiotemporal processes such as the climate and earth sciences. Here, we introduce an approach for efficient posterior estimation, using a Fourier Neural Operator (FNO) architecture with a flow matching objective. We show that our approach, FNOPE, can perform inference of function-valued parameters at a fraction of the simulation budget of state of the art methods. In addition, FNOPE supports posterior evaluation at arbitrary discretizations of the domain, as well as simultaneous estimation of vector-valued parameters. We demonstrate the effectiveness of our approach on several benchmark tasks and a challenging spatial inference task from glaciology. FNOPE extends the applicability of SBI methods to new scientific domains by enabling the inference of function-valued parameters.
Guy Moss、Leah Sophie Muhle、Reinhard Drews、Jakob H. Macke、Cornelius Schr?der
地球物理学大气科学(气象学)计算技术、计算机技术
Guy Moss,Leah Sophie Muhle,Reinhard Drews,Jakob H. Macke,Cornelius Schr?der.FNOPE: Simulation-based inference on function spaces with Fourier Neural Operators[EB/OL].(2025-05-28)[2025-07-16].https://arxiv.org/abs/2505.22573.点此复制
评论