AdaGrad-Norm last iterate achieves O(1/N^{1/4}) suboptimality for convex non-smooth problems, with tight lower bounds.
Y., Yurtsever, A., and Cevher, V
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Last Iterate Convergence of AdaGrad-Norm for Convex Non-Smooth Optimization
AdaGrad-Norm last iterate achieves O(1/N^{1/4}) suboptimality for convex non-smooth problems, with tight lower bounds.