jax.random.loggamma#

jax.random.loggamma(key, a, shape=None, dtype=<class 'numpy.float64'>)[source]#

Sample log-gamma random values with given shape and float dtype.

This function is implemented such that the following will hold for a dtype-appropriate tolerance:

np.testing.assert_allclose(jnp.exp(loggamma(*args)), gamma(*args), rtol=rtol)

The benefit of log-gamma is that for samples very close to zero (which occur frequently when a << 1) sampling in log space provides better precision.

Parameters

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

  • a (Union[Array, ndarray, bool_, number, bool, int, float, complex]) – a float or array of floats broadcast-compatible with shape representing the parameter of the distribution.

  • shape (Optional[Sequence[int]]) – optional, a tuple of nonnegative integers specifying the result shape. Must be broadcast-compatible with a. The default (None) produces a result shape equal to a.shape.

  • 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

Array

Returns

A random array with the specified dtype and with shape given by shape if shape is not None, or else by a.shape.

See also

gamma : standard gamma sampler.