Stability and Generalization for Stochastic Recursive Momentum-based Algorithms for (Strongly-)Convex One to K-Level Stochastic Optimizations.
Xiaokang PanXingyu LiJin LiuTao SunKai SunLixing ChenZhe QuPublished in: CoRR (2024)
Keyphrases
- stochastic search
- learning algorithm
- stochastic approximation
- orders of magnitude
- data structure
- lower bound
- worst case
- computational complexity
- stochastic model
- control policies
- significant improvement
- optimization problems
- theoretical analysis
- times faster
- generalization bounds
- recursive algorithm
- data sets
- approximation schemes