jax.random.generalized_normal(key, p, shape=(), dtype=<class 'numpy.float64'>)[source]#

Sample from the generalized normal distribution.

The values are returned according to the probability density function:

\[f(x;p) \propto e^{-|x|^p}\]

on the domain \(-\infty < x < \infty\), where \(p > 0\) is the shape parameter.

  • key (Union[Array, PRNGKeyArray]) – a PRNG key used as the random key.

  • p (float) – a float representing the shape parameter.

  • shape (Sequence[int]) – optional, the batch dimensions of the result. Default ().

  • dtype (Union[Any, str, dtype, SupportsDType]) – optional, a float dtype for the returned values (default float64 if jax_enable_x64 is true, otherwise float32).

Return type



A random array with the specified shape and dtype.