tfp.substrates.jax.math.log_bessel_ive

Computes log(tfp.math.bessel_ive(v, z)).

View aliases

Main aliases

tfp.experimental.substrates.jax.math.log_bessel_ive

tfp.substrates.jax.math.log_bessel_ive(
    v, z, name=None
)

This function is a more numerically stable version of log(tfp.math.bessel_ive(v, z)), along with more numerically stable gradients.

Warning: Gradients with respect to the first parameter v are currently not defined.

Args
v	Floating-point Tensor broadcastable with z for which log(Ive(v, z)) should be computed. v is expected to be non-negative.
z	Floating-point Tensor broadcastable with v for which log(Ive(v, z)) should be computed. If z is negative, v is expected to be an integer.
name	A name for the operation (optional). Default value: None (i.e., 'log_bessel_ive').

Returns
log_bessel_ive	Log of Exponentially modified Bessel Function of the first kind.