tfp.substrates.numpy.vi.chi_square

The chi-Square Csiszar-function in log-space.

tfp.substrates.numpy.vi.chi_square(
    logu, name=None
)

A Csiszar-function is a member of,

F = { f:R_+ to R : f convex }.

The Chi-square Csiszar-function is:

f(u) = u**2 - 1

logu float-like Tensor representing log(u) from above.
name Python str name prefixed to Ops created by this function.

chi_square_of_u float-like Tensor of the Csiszar-function evaluated at u = exp(logu).