SGD's last iterate reaches an O(log T / sqrt(T)) expected optimality gap for convex smooth stochastic problems under only convexity, smoothness, and finite gradient variance at a minimizer.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Last-Iterate Complexity of SGD for Convex and Smooth Stochastic Problems
SGD's last iterate reaches an O(log T / sqrt(T)) expected optimality gap for convex smooth stochastic problems under only convexity, smoothness, and finite gradient variance at a minimizer.