:py:mod:`ggt.losses.aleatoric_cov_loss`
=======================================

.. py:module:: ggt.losses.aleatoric_cov_loss


Module Contents
---------------


Functions
~~~~~~~~~

.. autoapisummary::

   ggt.losses.aleatoric_cov_loss.aleatoric_cov_loss



.. py:function:: aleatoric_cov_loss(outputs, targets, num_var=3, average=True)

   Computes the Aleatoric Loss while including the full
   covariance matrix of the outputs.

   If you are predicting for n output variables, then the
   number of output neuros required for this loss is
   (3n + n^2)/2.

   Args:
       outputs: (tensor) - predicted outputs from the model
       targets: (tensor) - ground truth labels
       size_average: (bool) - if True, the losses are
              averaged over all elements of the batch
   Returns:
       aleatoric_cov_loss: (tensor) - aleatoric loss

   Formula:
       loss = 0.5 * [Y - Y_hat].T * cov_mat_inv
               * [Y - Y_hat] + 0.5 * log(det(cov_mat))