Stochastic Optimization on L+-smooth functions
-1Iteration ComplexitySfyraki & Wang (2025)
Evaluation results
| Method | Links | |
|---|---|---|
| Sfyraki & Wang (2025)Stoc. Gradient Estimator=MVR2, Batch Size=O(ϵ^{-1})^d2025.09 | -1 | |
| Muon-MVR2Stoc. Gradient Estimator=MVR2, Batch Size=O(1)2025.09 | -1 |