Online Learning (Dynamic Regret Minimization) on Predictive Family Synthetic
16.14Mean Dynamic RegretPCGS
Evaluation results
| Method | Links | ||
|---|---|---|---|
| PCGSHorizon (T)=600, Expert Pool Size (K)=32, Number of sequences (N)=202026.03 | 16.14 | 0.59 | |
| GenShare(heur)Horizon (T)=600, Expert Pool Size (K)=32, Number of sequences (N)=202026.03 | 16.63 | 0.51 | |
| FixedShareHorizon (T)=600, Expert Pool Size (K)=32, Number of sequences (N)=202026.03 | 16.86 | 0.51 | |
| HedgeHorizon (T)=600, Expert Pool Size (K)=32, Number of sequences (N)=202026.03 | 21.04 | 1.85 |