Physics-Guided Conditional Flow Matching with Energy Regularization for Robust PDE Inverse Problems (Q7345569)

From MaRDI portal

!

This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:

No description defined
Language Label Description Also known as
default for all languages
No label defined
    English
    Physics-Guided Conditional Flow Matching with Energy Regularization for Robust PDE Inverse Problems
    No description defined

      Statements

      Physics-Guided Conditional Flow Matching with Energy Regularization for Robust PDE Inverse Problems (English)
      0 references
      14 September 2026
      0 references
      math.NA
      0 references
      Yongsheng Chen
      0 references
      Shuo Lu
      0 references
      Wei Guo
      0 references
      Xinghui Zhong
      0 references
      We develop physics-guided conditional flow matching with energy regularization for solving PDE inverse problems from sparse noisy observations by incorporating strong-form PDE information through residual regularization along generative trajectories and assigning each observation a physics-data energy score, achieving state-of-the-art accuracy on several benchmarks.
      0 references
      Physics-Guided
      0 references
      Conditional Flow Matching
      0 references
      PDE Inverse Problems
      0 references

      Identifiers

      0 references
      0 references
      0 references
      0 references