tfp.substrates.numpy.math.igammacinv

Computes the inverse to tf.math.igammac with respect to p.

View aliases

Main aliases

tfp.experimental.substrates.numpy.math.igammacinv

tfp.substrates.numpy.math.igammacinv(
    a, p, name=None
)

This function is defined as the solution x to the equation p = tf.math.igammac(a, x).

References

[1] A. Didonato and A. Morris, Computation of the Incomplete Gamma Function Ratios and their Inverse https://dl.acm.org/doi/10.1145/22721.23109

Args
a	A positive float Tensor. Must be broadcastable with p.
p	A float Tensor whose entries lie in [0, 1]. Must be broadcastable with a.
name	Optional Python str naming the operation.

Returns
igammacinv	igammacinv(a, p). Has same type as a.