AI RESEARCH
Unified High-Probability Analysis of Stochastic Variance-Reduced Estimation
arXiv CS.LG
•
ArXi:2605.15388v1 Announce Type: new Stochastic estimators are fundamental to large-scale optimization, where population quantities must be inferred from noisy oracle observations. Although influential methods such as momentum, SPIDER, STORM, and PAGE have been highly successful, their analyses are largely estimator-specific and expectation-based, obscuring the structural tradeoffs that determine reliability.