tfa.losses.PinballLoss

Computes the pinball loss between y_true and y_pred.

tfa.losses.PinballLoss(
    tau: tfa.types.FloatTensorLike = 0.5,
    reduction: str = tf.keras.losses.Reduction.AUTO,
    name: str = 'pinball_loss'
)

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:

pinball = tfa.losses.PinballLoss(tau=.1)
loss = pinball([0., 0., 1., 1.], [1., 1., 1., 0.])
loss
<tf.Tensor: shape=(), dtype=float32, numpy=0.475>

Usage with the tf.keras API:

model = tf.keras.Model()
model.compile('sgd', loss=tfa.losses.PinballLoss(tau=.1))

Args
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).
reduction	(Optional) Type of tf.keras.losses.Reduction to apply to loss. Default value is AUTO. AUTO indicates that the reduction option will be determined by the usage context. For almost all cases this defaults to SUM_OVER_BATCH_SIZE. When used with tf.distribute.Strategy, outside of built-in training loops such as tf.keras compile and fit, using AUTO or SUM_OVER_BATCH_SIZE will raise an error. Please see https://www.tensorflow.org/alpha/tutorials/distribute/training_loops for more details on this.
name	Optional name for the op.

References
https://en.wikipedia.org/wiki/Quantile_regression https://projecteuclid.org/download/pdfview_1/euclid.bj/1297173840

Methods

from_config

@classmethod
from_config(
    config
)

Instantiates a Loss from its config (output of get_config()).

Args
config	Output of get_config().

Returns
A Loss instance.

get_config

View source

get_config()

Returns the config dictionary for a Loss instance.

__call__

__call__(
    y_true, y_pred, sample_weight=None
)

Invokes the Loss instance.

Args
y_true	Ground truth values. shape = [batch_size, d0, .. dN], except sparse loss functions such as sparse categorical crossentropy where shape = [batch_size, d0, .. dN-1]
y_pred	The predicted values. shape = [batch_size, d0, .. dN]
sample_weight	Optional sample_weight acts as a coefficient for the loss. If a scalar is provided, then the loss is simply scaled by the given value. If sample_weight is a tensor of size [batch_size], then the total loss for each sample of the batch is rescaled by the corresponding element in the sample_weight vector. If the shape of sample_weight is [batch_size, d0, .. dN-1] (or can be broadcasted to this shape), then each loss element of y_pred is scaled by the corresponding value of sample_weight. (Note ondN-1: all loss functions reduce by 1 dimension, usually axis=-1.)

Returns
Weighted loss float Tensor. If reduction is NONE, this has shape [batch_size, d0, .. dN-1]; otherwise, it is scalar. (Note dN-1 because all loss functions reduce by 1 dimension, usually axis=-1.)

Raises
ValueError	If the shape of sample_weight is invalid.