jaxopt.objective.multiclass_logreg
- jaxopt.objective.multiclass_logreg = <jaxopt._src.objective.MulticlassLogreg object>
Multiclass logistic regression.
\[\frac{1}{n} \sum_{i=1}^n \ell(W^\top x_i, y_i)\]where \(\ell\) is
multiclass_logistic_loss
andX, y = data
.- Parameters
W – a matrix of shape
(n_features, n_classes)
.data – a tuple
(X, y)
whereX
is a matrix of shape(n_samples, n_features)
andy
is a vector of shape(n_samples,)
.
- Returns
objective value.
Example:
value = multiclass_logreg(W, (X, y))