[MRG] DOC: plot_enet improved

QB3 / sparse-ho

Fast hyperparameter settings for non-smooth estimators:

http://qb3.github.io/sparse-ho

BSD 3-Clause "New" or "Revised" License

38 stars 15 forks source link

Closed mathurinm closed 3 years ago

mathurinm commented 3 years ago

Picked a bigger n_samples (20 was low)

Start at alpha_max * 0.9 (it does not hurt convergence)

Linked iterates with a thin line

Used celer.datasets.make_correlated_data as I don't know if noise=1 in sklearn.datasets.make_regression is high or not.

Time grid search 2.648443
Time grad-search 1.162781
Minimum grid search 2.268e+01
Minimum grad search 2.257e+01

agramfort commented 3 years ago

looks good !