Near-Optimal Learning of Gaussian Sobolev Operators (Q7284035)
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 | Near-Optimal Learning of Gaussian Sobolev Operators |
No description defined |
Statements
Near-Optimal Learning of Gaussian Sobolev Operators (English)
0 references
8 July 2026
0 references
math.NA
0 references
cs.IT
0 references
cs.LG
0 references
Ben Adcock
0 references
Michael Griebel
0 references
Gregor Maier
0 references
We present an algorithm, Hermite-PCA approximation, that learns Gaussian Sobolev operators efficiently by combining principal component analysis and weighted least-squares methods, achieving near-optimal sample complexity rates for a wide range of regularities.
0 references
Operator Learning
0 references
Gaussian Operators
0 references
Sobolev Spaces
0 references
Approximation Guarantees
0 references
