tfa.losses.pinball_loss

View source on GitHub

Computes the pinball loss between y_true and y_pred.

loss = maximum(tau * (y_true - y_pred), (tau - 1) * (y_true - y_pred))

In the context of regression this, loss yields an estimator of the tau conditional quantile.

See: https://en.wikipedia.org/wiki/Quantile_regression

Usage:

loss = pinball_loss([0., 0., 1., 1.], [1., 1., 1., 0.], tau=.1)

# loss = max(0.1 * (y_true - y_pred), (0.1 - 1) * (y_true - y_pred))
#      = (0.9 + 0.9 + 0 + 0.1) / 4

print('Loss: ', loss.numpy())  # Loss: 0.475

Args:

  • y_true: Ground truth values. shape = [batch_size, d0, .. dN]
  • y_pred: The predicted values. shape = [batch_size, d0, .. dN]
  • tau: (Optional) Float in [0, 1] or a tensor taking values in [0, 1] and shape = [d0,..., dn]. It defines the slope of the pinball loss. In the context of quantile regression, the value of tau determines the conditional quantile level. When tau = 0.5, this amounts to l1 regression, an estimator of the conditional median (0.5 quantile).

Returns:

  • pinball_loss: 1-D float Tensor with shape [batch_size].

References: