Kernel learning on HMK synthetic data 1.0 (test)
56.8Relative ErrorNGSM
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| NGSMhidden layers=2, units=1282026.02 | 56.8 | 0.35 | 13.4 | |
| Regular Fourier Features (real)network output=real-valued, features (m)=255, cutoff frequency=10, rank (r)=8, hidden layers=2, units=1282026.02 | 57.5 | 0.56 | 10.7 | |
| Regular Fourier Features (complex)network output=complex-valued, features (m)=255, cutoff frequency=10, rank (r)=8, hidden layers=2, units=1282026.02 | 76.9 | 0.55 | 10.3 | |
| NNK2026.02 | 100 | 1.46 | 4,075.7 | |
| RBF2026.02 | 134.5 | 0.03 | 704 | |
| DKLhidden layers=2, units=1282026.02 | 309.4 | 1.49 | 39 |