Consistency Training with Physical Constraints
This work addresses the challenge of efficient sampling for solving partial differential equations using deep generative modeling, but it appears incremental as it builds on existing consistency training methods.
The paper tackles the problem of accelerating sampling in Diffusion Models by incorporating physical constraints, resulting in a method that generates samples in a single step while adhering to these constraints.
We propose a physics-aware Consistency Training (CT) method that accelerates sampling in Diffusion Models with physical constraints. Our approach leverages a two-stage strategy: (1) learning the noise-to-data mapping via CT, and (2) incorporating physics constraints as a regularizer. Experiments on toy examples show that our method generates samples in a single step while adhering to the imposed constraints. This approach has the potential to efficiently solve partial differential equations (PDEs) using deep generative modeling.