evidential_regression_regularization

probly.losses.torch.evidential_regression_regularization(inputs: dict[str, Tensor], targets: Tensor) → Tensor

Evidential regression regularizer from [ASSR20].

Implements the evidence regularization component to penalize confident but inaccurate predictions in Deep Evidential Regression.

Parameters:

• inputs – Dictionary containing evidential regression parameters with keys "gamma", "nu", and "alpha", each of shape (B,).

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

Returns:

Scalar evidential regression regularization loss averaged over the batch.