Variance Reduction Note 2: The Convergence of SPIDER
The stochastic path-integrated differential estimator (SPIDER) tracks a gradient by accumulating small, shared-sample gradient differences and periodically refreshing the estimate. This second expository note on recursive variance reduction explains SPIDER-SFO and gives a self-contained proof of its expected first-order stationarity guarantee. The argument combines an epochwise mean-square error bound with descent under a clipped, normalized update. It yields $O(ε^{-3})$ stochastic gradient evaluations in the online setting and $O(n+\sqrt n\,ε^{-2})$ component gradient evaluations for a finite sum, with the remaining problem parameters fixed. All refresh costs are included. The presentation is pedagogical and makes no claim of a new algorithm or convergence rate.