Making the last iterate of SGD information theoretically optimal (Q4987277)
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 7341861
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Making the last iterate of SGD information theoretically optimal |
scientific article; zbMATH DE number 7341861 |
Statements
Making the Last Iterate of SGD Information Theoretically Optimal (English)
0 references
3 May 2021
0 references
stochastic gradient descent
0 references
convex optimization
0 references
gradient descent
0 references
last iterate guarantees
0 references
0 references
0.7348769903182983
0 references
0.7346042394638062
0 references
0.717124342918396
0 references
0.7131503820419312
0 references
0.7073835134506226
0 references
