Adaptive Variance Reduction for Stochastic Optimization under Weaker
Assumptions
Adaptive Variance Reduction for Stochastic Optimization under Weaker
Assumptions
This paper explores adaptive variance reduction methods for stochastic optimization based on the STORM technique. Existing adaptive extensions of STORM rely on strong assumptions like bounded gradients and bounded function values, or suffer an additional $\mathcal{O}(\log T)$ term in the convergence rate. To address these limitations, we introduce a novel …