Next-step prediction on Synthetic HMM Overcomplete case N=1000
0.737Validation LossHMM Filter
Evaluation results
| Method | Links | |
|---|---|---|
| HMM Filter2025.11 | 0.737 | |
| nanoGPT-m# parameters=199,232, training time=1.5 min, # iterations=2,000 iter.2025.11 | 0.81 | |
| nanoGPT-s# parameters=51,392, training time=1 min, # iterations=2,000 iter.2025.11 | 0.829 | |
| Belief Net# parameters=6,208, training time=6 min, # iterations=2,000 iter.2025.11 | 0.83 | |
| Baum-Welch# parameters=6,208, training time=12 min, # iterations=20 iter.2025.11 | 1.216 | |
| Random2025.11 | 3.466 |