merge_spline_lf_opts: Merge in default options for spline_lf()
In krisrs1128/LFExpers: Experiments in Latent Factor Modeling

Merge in default options for spline_lf()

1	merge_spline_lf_opts(opts = list())

opts

A potentially partially specified list, which we will merge in with defaults. Please include new parameters in alphabetical order. The possible options, and their defaults are,
$alpha The tradeoff between l1 and l2 penalties in the elastic net.
$lambda The overall regularization parameter in the elastic net.
$nu The learning rate / step-size for the coordinate descent. Arbitrarily defaults to 1e-5. If things are not converging, try making this smaller.
$n_iter The number of steps of the alternating minimization to perform.
$n_iter_B The number of sweeps over all entries of B via coordinate descent.

The modified opts list, with defaults filled in for entries that had been missing.

krisrs1128/LFExpers documentation built on May 20, 2019, 1:25 p.m.