der_loss

probly.losses.torch.der_loss(y: Tensor, mu: Tensor, kappa: Tensor, alpha: Tensor, beta: Tensor, lam: float = 0.01) → Tensor

Deep Evidential Regression loss from [ASSR20].

Combines a Student-t negative log-likelihood with an evidence regularization term for uncertainty-aware regression.

Parameters:

• y – Ground-truth regression targets, shape (B,) or (B, 1).

• mu – Predicted mean of the Normal-Inverse-Gamma distribution, shape (B,).

• kappa – Predicted scaling parameter, shape (B,).

• alpha – Predicted shape parameter, shape (B,).

• beta – Predicted scale parameter, shape (B,).

• lam – Weight of the evidence regularization term.

Returns:

Scalar Deep Evidential Regression loss averaged over the batch.