ird_loss

probly.losses.torch.ird_loss(alpha: Tensor, y: Tensor, adversarial_alpha: Tensor | None = None, p: float = 2.0, lam: float = 1.0, gamma: float = 1.0, normalize: bool = True) → Tensor[source]

Information Robust Dirichlet loss from [Tsi19].

Implements the Information Robust Dirichlet (IRD) loss, combining an Lp calibration term, a trigamma-based regularization term, and an optional entropy-based adversarial regularizer.

Parameters:

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

  • y – One-hot encoded class labels, shape (B, K).

  • adversarial_alpha – Dirichlet concentration parameters for adversarial inputs, shape (B_a, K).

  • p – Lp norm exponent controlling calibration strength.

  • lam – Weight of the regularization term.

  • gamma – Weight of the entropy regularization term.

  • normalize – Whether to normalize loss terms by batch size.

Returns:

Scalar IRD loss summed over all input examples.