Math 2.0

Resources / preprint

Revisiting AdaGrad in Stochastic Convex Optimization: Last Iterates, High Probability, and Lower Bounds PGJ37WRB1K

URIm2://res/PGJ37WRB1K
Kindpreprint
CreatorsWeiming Ou, Xiao Wang
Date2026-09-26
MSC49-XX, 90-XX, 93-XX
Subjectsarxiv math.OC, arxiv cs.LG
Scopein

Expressions

e1: version, preprint

Languageen
Date2026-09-26
IdsarXiv 2609.32729

Items in this resource

The mentions of the inventory that name this resource. Each name links to the card of its inventory row.

ItemKindWhereSource
1HWMPR23HHdefinitiondefinitionarxiv
Constant worst-case error under bounded variancestatementtheorem 3.8arxiv
A scalar logarithmic average-error lower boundstatementtheorem 3.10arxiv
No polynomial average-iterate rate with polylogarithmic confidencestatementtheorem 3.5arxiv
Noise-adaptive average-iterate upper boundsstatementtheorem 3.14arxiv
Arbitrarily slow last-iterate convergencestatementtheorem 3.1arxiv

Catalogue records