Denoising growth complexity: Data geometry and certified schedules for diffusion sampling (Q7284585)
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 | Denoising growth complexity: Data geometry and certified schedules for diffusion sampling |
No description defined |
Statements
Denoising growth complexity: Data geometry and certified schedules for diffusion sampling (English)
0 references
28 July 2026
0 references
math.ST
0 references
cs.LG
0 references
math.NA
0 references
stat.ML
0 references
Martin J. Wainwright
0 references
We introduce denoising growth complexity ($\mathsf{DGC}$) as a geometric measure of diffusion-based sampling algorithms' performance and derive certified schedules based on it that outperform uniform stepsize in certain regimes.
0 references
Denoising Growth Complexity
0 references
Data Geometry
0 references
Certified Schedules
0 references
Diffusion Sampling
0 references
