Convergence Analysis on General Optimization
1Convergence RateSD
Evaluation results
| Method | Links | |
|---|---|---|
| SDWeight Decay=Without, Model=General, Smooth Assumption=✓, L.C. Assumption=×2026.05 | 1 | |
| SD & MuonWeight Decay=Without, Model=General(nonconvex), Smooth Assumption=✓, L.C. Assumption=×2026.05 | 1 | |
| SD & MuonWeight Decay=Without, Model=General(nonconvex), Smooth Assumption=✓, L.C. Assumption=×, Reference=(Li and Hong, 2025)2026.05 | 1 | |
| SDWeight Decay=Without, Model=General, Smooth Assumption=×, L.C. Assumption=✓, Source=Theorem 4.12026.05 | 1 | |
| TSDWeight Decay=Without, Model=General, Smooth Assumption=×, L.C. Assumption=✓, Source=Theorem 4.22026.05 | 1 | |
| MuonWWeight Decay=With, Model=General, Smooth Assumption=✓, L.C. Assumption=×2026.05 | 1 | |
| RSD-WDWeight Decay=With, Model=General, Smooth Assumption=×, L.C. Assumption=✓, Source=Theorem 4.32026.05 | 1 | |
| RTSD-WDWeight Decay=With, Model=General, Smooth Assumption=×, L.C. Assumption=✓, Source=Theorem 4.42026.05 | 1 |