Ultra Fast PDE Solving via Physics Guided Few-step Diffusion
This addresses the problem of slow and physically inconsistent PDE solving for researchers and practitioners in scientific computing, representing a strong specific gain rather than a foundational advancement.
The paper tackles the high sampling costs and insufficient physical consistency of diffusion-based PDE solvers by proposing Phys-Instruct, a physics-guided distillation framework that compresses pre-trained models into few-step generators and injects PDE knowledge, achieving orders-of-magnitude faster inference and reducing PDE error by more than 8 times compared to state-of-the-art baselines across five benchmarks.
Diffusion-based models have demonstrated impressive accuracy and generalization in solving partial differential equations (PDEs). However, they still face significant limitations, such as high sampling costs and insufficient physical consistency, stemming from their many-step iterative sampling mechanism and lack of explicit physics constraints. To address these issues, we propose Phys-Instruct, a novel physics-guided distillation framework which not only (1) compresses a pre-trained diffusion PDE solver into a few-step generator via matching generator and prior diffusion distributions to enable rapid sampling, but also (2) enhances the physics consistency by explicitly injecting PDE knowledge through a PDE distillation guidance. Physic-Instruct is built upon a solid theoretical foundation, leading to a practical physics-constrained training objective that admits tractable gradients. Across five PDE benchmarks, Phys-Instruct achieves orders-of-magnitude faster inference while reducing PDE error by more than 8 times compared to state-of-the-art diffusion baselines. Moreover, the resulting unconditional student model functions as a compact prior, enabling efficient and physically consistent inference for various downstream conditional tasks. Our results indicate that Phys-Instruct is a novel, effective, and efficient framework for ultra-fast PDE solving powered by deep generative models.