method | dim | neighbors/σ | loo-cv accuracy |
---|
PCA | 14 | - | 87.4 |
KPCA | 15 | 5e5 | 87.1 |
LLE | 12 | 14 | 88.5 |
IM | 8 | 10 | 85 |
IM(mod) | 15 | 4 | 87.4 |
LEM | 5 | 4 | 85.3 |
DM | 13 | 5e5 | 84.3 |
MVU | 5 | 14 | 85 |
- All parameters of the dimension reduction techniques for the Wang et al. breast cancer dataset, estimated by leave-one-out cross-validation. PCA has no additional parameter, while KPCA and DM have a kernel parameter σ and IM, LEM and MVU take the number of neighbors as argument.