Runs for Beeline models

[DesmondYuan]

Env created for testing those models here 881527314fe1b49eef92b50ccd6a9869d48468ef

I suggest we split the tasks into 3. A quick look suggests that cyclic and bifurcation networks are relatively harder to train.

• [x] Synthetic Bifurcate (BF, BFC, TF)
• [x] Synthetic Cyclic (CY)
• [x] linear (LI, LL)
• [x] Curated VSC
• [x] Curated mCAD
• [x] Curated HSC
• [x] Curated GSD

[DesmondYuan]

Curated models e8a45404c91d6469d57bcdf2d8186eddfe40ef9b

Curated models are roughly harder to train. Probably because of the network degree which is different from synthetic models. Adding # of conditions or decrease alpha to 0.2 helps.

• mCAD can be trained with n_mu=5 and n_mu=1
• VSC and HSC can be trained with n_mu=2 at least
• GSD can be trained with n_mu=19 and n_mu=2 at least (weight_decay:1e-12->1e-8->1e-6->1e-4)

All with train/valid/test=100/10/10 and ntotal=5 (ts=0:4:20) Adding a schedule for increasing weight_decay helps too 'can be trained' as in the MAE<=1e-3 and parameter strongly correlated to ground truth

[judyueshen]

Synthetic CY trained with the config and new network file in commit https://github.com/jiweiqi/CellBox.jl/commit/95830d2dd0a5bbd5526c095becc58bf46a02ca41

alpha is set to 1.0. n_mu=2 and n_exp_train=20. There is still a nice tendency to oscillate :)

[judyueshen]

Bifurcating configs in commit 650b9cf698c34e18ebc0206940b37525b3ec8379 alpha is set to 0.2. For optimal parameter learning, ntotal and n_exp_train need to be slightly bigger than the given configs.