Jensen-Shannon Divergence

Compute the Jensen-Shannon divergence.

Where $P$ and $Q$ are probability distributions where $P$ usually represents a distribution over data and $Q$ is often a prior or approximation of $P$. $D_{KL}$ is the KL divergence and $M$ is the average of the two distributions. It should be noted that the Jensen-Shannon divergence is a symmetrical metric i.e. $D_{JS}(P||Q)=D_{JS}(Q||P)$.

As input to forward and update the metric accepts the following input:

• p (Tensor): a data distribution with shape (N, d)

• q (Tensor): prior or approximate distribution with shape (N, d)

As output of forward and compute the metric returns the following output:

• js_divergence (Tensor): A tensor with the Jensen-Shannon divergence

Parameters:

• log_prob (bool) – bool indicating if input is log-probabilities or probabilities. If given as probabilities, will normalize to make sure the distributes sum to 1.

• reduction (Literal['mean', 'sum', 'none', None]) –

  Determines how to reduce over the N/batch dimension:

  • 'mean' [default]: Averages score across samples

  • 'sum': Sum score across samples

  • 'none' or None: Returns score per sample

• kwargs (Any) – Additional keyword arguments, see Advanced metric settings for more info.

Raises:

• TypeError – If log_prob is not an bool.

• ValueError – If reduction is not one of 'mean', 'sum', 'none' or None.

Example

>>> from torch import tensor
>>> from torchmetrics.regression import JensenShannonDivergence
>>> p = tensor([[0.1, 0.9], [0.2, 0.8], [0.3, 0.7]])
>>> q = tensor([[0.3, 0.7], [0.4, 0.6], [0.5, 0.5]])
>>> js_div = JensenShannonDivergence()
>>> js_div(p, q)
tensor(0.0259)

plot(val=None, ax=None)[source]

Plot a single or multiple values from the metric.

Parameters:

• val (Union[Tensor, Sequence[Tensor], None]) – Either a single result from calling metric.forward or metric.compute or a list of these results. If no value is provided, will automatically call metric.compute and plot that result.

• ax (Optional[Axes]) – An matplotlib axis object. If provided will add plot to that axis

Return type:

tuple[Figure, Union[Axes, ndarray]]

Returns:

Figure and Axes object

Raises:

ModuleNotFoundError – If matplotlib is not installed

>>>

>>> from torch import randn
>>> # Example plotting a single value
>>> from torchmetrics.regression import KLDivergence
>>> metric = KLDivergence()
>>> metric.update(randn(10,3).softmax(dim=-1), randn(10,3).softmax(dim=-1))
>>> fig_, ax_ = metric.plot()

>>>

>>> from torch import randn
>>> # Example plotting multiple values
>>> from torchmetrics.regression import KLDivergence
>>> metric = KLDivergence()
>>> values = []
>>> for _ in range(10):
...     values.append(metric(randn(10,3).softmax(dim=-1), randn(10,3).softmax(dim=-1)))
>>> fig, ax = metric.plot(values)