TensorFlow 2.0 RC is available Learn more

tfp.vi.chi_square

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

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

Defined in python/vi/csiszar_divergence.py.

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

Args:

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

Returns:

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