Probability-Flow ODE in Infinite-Dimensional Function Spaces
By: Kunwoo Na , Junghyun Lee , Se-Young Yun and more
Potential Business Impact:
Makes AI draw complex things much faster.
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.
Similar Papers
Adaptivity and Convergence of Probability Flow ODEs in Diffusion Generative Models
Machine Learning (Stat)
Makes AI create realistic pictures faster.
Integration Flow Models
CV and Pattern Recognition
Makes AI create better pictures faster.
Minimax Optimality of the Probability Flow ODE for Diffusion Models
Machine Learning (CS)
Makes AI create realistic pictures more accurately.