Low Dimensional Landscape Hypothesis is True: DNNs can be Trained in Tiny Subspaces (Q6363322)
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: Low Dimensional Landscape Hypothesis is True: DNNs can be Trained in Tiny Subspaces |
preprint article from arXiv
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Low Dimensional Landscape Hypothesis is True: DNNs can be Trained in Tiny Subspaces |
preprint article from arXiv |
Statements
20 March 2021
0 references
cs.LG
0 references
cs.NE
0 references
math.OC
0 references
Tao Li
0 references
Lei Tan
0 references
Qinghua Tao
0 references
Yipeng Liu
0 references
Xiaolin Huang
0 references
