probly.train.evidential.torch.evidential_regression_regularization

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

Regularization term for evidential regression.

Implements the evidence regularization component proposed by Amini et al. (2020) to penalize confident but inaccurate predictions in Deep Evidential Regression.

Reference:

Amini et al., “Deep Evidential Regression”, NeurIPS 2020. https://arxiv.org/abs/1910.02600

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.