tfp.substrates.numpy.vi.squared_hellinger

The Squared-Hellinger Csiszar-function in log-space.

View aliases

Main aliases

tfp.experimental.substrates.numpy.vi.squared_hellinger

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

A Csiszar-function is a member of,

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

The Squared-Hellinger Csiszar-function is:

f(u) = (sqrt(u) - 1)**2

This Csiszar-function induces a symmetric f-Divergence, i.e., D_f[p, q] = D_f[q, p].

Warning: this function makes non-log-space calculations and may therefore be numerically unstable for |logu| >> 0.

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

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