Intel® oneAPI Data Analytics Library Developer Guide and Reference
Logistic Loss
LogisticLoss is a common objective function used for binary classification.
Operation |
Computational methods |
|
Mathematical formulation
Computing
Algorithm takes dataset with n feature vectors of dimension p, vector with correct class labels
and coefficients vector
of size
as input. Then it calculates logistic loss, its gradient or gradient using the following formulas.
Value
, where
- predicted probabilities,
- sigmoid function. Note that probabilities are binded to interval
to avoid problems with computing log function (
if float type is used and
otherwise)
Gradient
, where
,
for
Hessian
, where
,
,
for
Computation method: dense_batch
The method computes value of objective function, its gradient or hessian for the dense data. This is the default and the only method supported.
Programming Interface
Refer to API Reference: LogisticLoss.
Distributed mode
Currently algorithm does not support distributed execution in SMPD mode.