DERLoss#

class torch_uncertainty.losses.DERLoss(reg_weight, reduction='mean')[source]#

The Deep Evidential Regression loss.

This loss combines the negative log-likelihood loss of the normal inverse gamma distribution and a weighted regularization term.

Parameters:
  • reg_weight (float) – The weight of the regularization term.

  • reduction (str, optional) – specifies the reduction to apply to the output:'none' | 'mean' | 'sum'.

References

[1] Amini, A., Schwarting, W., Soleimany, A., & Rus, D. (2019). Deep evidential regression.