Table 6 Hyperparameter search spaces for inductor models in SEQENS

KNeighbors

n_neighbors

2 — 10

weights

[uniform, distance]

leaf_size

10 — 50

RandomForest

n_estimators

20 — 100

min_samples_split

2 — 20

min_samples_leaf

1 — 10

max_depth

1 — 10

max_features

[sqrt, log2]

XGBoost

booster

[gbtree]

objective

[binary:logistic]

n_estimators

50 — 150

learning_rate

0.001 — 1

max_depth

1 — 10

grow_policy

[depthwise, lossguide]

subsample

0.8 — 1

colsample_bytree

0.5 — 1

colsample_bylevel

0.5 — 1

colsample_bynode

0.5 — 1

reg_alpha

0.0001 — 1

reg_lambda

0.0001 — 1

GradientBoosting

loss

[log_loss]

n_estimators

20 — 100

learning_rate

0.01 — 1

max_depth

1 — 8

min_samples_leaf

1 — 10

min_samples_split

2 — 20

subsample

0.8 — 1

max_features

[sqrt, log2]

SupportVector

C

0.1 — 10

kernel

[linear, rbf]

gamma

[scale, auto]