Adaptive Gradient Methods Converge Faster with Over-Parameterization (but you should do a line-search) (Q6342704)
From MaRDI portal
preprint article from arXiv
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Adaptive Gradient Methods Converge Faster with Over-Parameterization (but you should do a line-search) |
preprint article from arXiv |
Statements
11 June 2020
0 references
cs.LG
0 references
math.OC
0 references
stat.ML
0 references
Sharan Vaswani
0 references
Issam Laradji
0 references
Frederik Kunstner
0 references
Si Yi Meng
0 references
Mark Schmidt
0 references
Simon Lacoste-Julien
0 references
