REVIEW 2 cited by
Probability-Flow ODE in Infinite-Dimensional Function Spaces
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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.
Forward citations
Cited by 2 Pith papers
-
Discretization and Statistical Consistency of Functional Flow Matching
Finite conditional velocity targets in functional flow matching converge in L2 to the continuum target under nonnested, strongly consistent reconstructions, with end-to-end Wasserstein control of the generated laws.
-
Physics-informed diffusion models in spectral space
A spectral-latent diffusion model with physics and observation guidance at inference solves forward and inverse PDE problems from sparse data with claimed large speedups.
Discussion (0). Continue with ORCID to comment.