tfp.substrates.jax.vi.pearson

The Pearson Csiszar-function in log-space.

Main aliases

tfp.experimental.substrates.jax.vi.pearson

tfp.substrates.jax.vi.pearson(
    logu, name=None
)

A Csiszar-function is a member of,

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

The Pearson Csiszar-function is:

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

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

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

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2023-11-21 UTC.

Args