natpn_loss

probly.losses.torch.natpn_loss(alpha: Tensor, y: Tensor, entropy_weight: float = 0.0001) → Tensor[source]

Natural Posterior Network loss from [CBZugner+22].

Implements the Dirichlet-Categorical Bayesian loss with an entropy regularizer for Natural Posterior Network (NatPN) classification.

Parameters:

  • alpha – Posterior Dirichlet concentration parameters, shape (B, C).

  • y – Ground-truth class labels, shape (B,) with values in [0, C-1].

  • entropy_weight – Weight controlling the strength of the entropy regularization term.

Returns:

Scalar NatPN loss averaged over the batch.