Optimal Sobolev Approximation by Deterministic and Random Shallow Sigmoidal Networks (Q7284947)
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 | Optimal Sobolev Approximation by Deterministic and Random Shallow Sigmoidal Networks |
No description defined |
Statements
Optimal Sobolev Approximation by Deterministic and Random Shallow Sigmoidal Networks (English)
0 references
20 August 2026
0 references
math.NA
0 references
Zhaohui Fu
0 references
Yangshuai Wang
0 references
We establish the optimal approximation power by shallow networks with smooth sigmoidal activations in general dimension. We show that both deterministic and randomly sampled hidden parameters can achieve the same optimal rate up to logarithmic oversampling.
0 references
Sobolev Approximation
0 references
Shallow Networks
0 references
Deterministic vs Random
0 references
