PMQSopt achieves expected O(T^{-1/4}) convergence rates for three epsilon-KKT metrics after T iterations in weakly convex stochastic programming under weak convexity and strict feasibility assumptions.
Shalev-Shwartz, Online learning and online convex optimization,Foundations and Trends in Machine Learning, 4:2 (2011), 107–194
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
-
A Quadratic-Approximation-Based Stochastic Approximation Method for Weakly Convex Stochastic Programming
PMQSopt achieves expected O(T^{-1/4}) convergence rates for three epsilon-KKT metrics after T iterations in weakly convex stochastic programming under weak convexity and strict feasibility assumptions.