Stability and Generalization for Stochastic Recursive Momentum-based Algorithms for (Strongly-)Convex One to $K$-Level Stochastic Optimizations

Xiaokang Pan, Xingyu Li, Jin Liu +4

STOchastic Recursive Momentum (STORM)-based algorithms have been widely developed to solve one to $K$-level ($K\ge 3$) stochastic optimization problems. Specifically, they use es…