Score: 0

Probability-Flow ODE in Infinite-Dimensional Function Spaces

Published: March 13, 2025 | arXiv ID: 2503.10219v1

By: Kunwoo Na , Junghyun Lee , Se-Young Yun and more

Potential Business Impact:

Makes AI draw complex things much faster.

Business Areas:
Innovation Management Professional Services

Recent advances in infinite-dimensional diffusion models have demonstrated their effectiveness and scalability in function generation tasks where the underlying structure is inherently infinite-dimensional. To accelerate inference in such models, we derive, for the first time, an analog of the probability-flow ODE (PF-ODE) in infinite-dimensional function spaces. Leveraging this newly formulated PF-ODE, we reduce the number of function evaluations while maintaining sample quality in function generation tasks, including applications to PDEs.

Country of Origin
🇰🇷 Korea, Republic of

Page Count
26 pages

Category
Computer Science:
Machine Learning (CS)