Gradient descent provably escapes saddle points in the training of shallow ReLU networks (Q6655804)
From MaRDI portal
 | This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: Gradient descent provably escapes saddle points in the training of shallow ReLU networks |
scientific article; zbMATH DE number 7960846
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Gradient descent provably escapes saddle points in the training of shallow ReLU networks |
scientific article; zbMATH DE number 7960846 |
Statements
Gradient descent provably escapes saddle points in the training of shallow ReLU networks (English)
0 references
27 December 2024
0 references
neural networks
0 references
center-stable manifolds
0 references
gradient descent
0 references
nonconvex optimization
0 references
0 references
0 references
0 references
0 references
