An Efficient Conditional Score-based Filter for High Dimensional Nonlinear Filtering Problems
This addresses a critical problem in engineering and applied sciences where existing methods are impractical for high-dimensional systems.
The paper tackles the challenge of high-dimensional nonlinear filtering by proposing the Conditional Score-based Filter (CSF), which uses a set-transformer encoder and conditional diffusion model to achieve efficient posterior sampling without retraining, resulting in superior accuracy, robustness, and efficiency in experiments.
In many engineering and applied science domains, high-dimensional nonlinear filtering is still a challenging problem. Recent advances in score-based diffusion models offer a promising alternative for posterior sampling but require repeated retraining to track evolving priors, which is impractical in high dimensions. In this work, we propose the Conditional Score-based Filter (CSF), a novel algorithm that leverages a set-transformer encoder and a conditional diffusion model to achieve efficient and accurate posterior sampling without retraining. By decoupling prior modeling and posterior sampling into offline and online stages, CSF enables scalable score-based filtering across diverse nonlinear systems. Extensive experiments on benchmark problems show that CSF achieves superior accuracy, robustness, and efficiency across diverse nonlinear filtering scenarios.