Gradient descent optimizes over-parameterized deep ReLU networks (Q2183586)
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:
scientific article; zbMATH DE number 7205217
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Gradient descent optimizes over-parameterized deep ReLU networks |
scientific article; zbMATH DE number 7205217 |
Statements
Gradient descent optimizes over-parameterized deep ReLU networks (English)
0 references
27 May 2020
0 references
deep neural networks
0 references
gradient descent
0 references
over-parameterization
0 references
random initialization
0 references
global convergence
0 references
0.7682542204856873
0 references
0.7526460289955139
0 references
0.7521389722824097
0 references
0.7511272430419922
0 references
0.7506621479988098
0 references
