vi_triangular

The Triangular Csiszar-function is:

Interface to 'TensorFlow Probability', a 'Python' library built on 'TensorFlow'
that makes it easy to combine probabilistic models and deep learning on modern hardware ('TPU', 'GPU').
'TensorFlow Probability' includes a wide selection of probability distributions and bijectors, probabilistic layers,
variational inference, Markov chain Monte Carlo, and optimizers such as Nelder-Mead, BFGS, and SGLD.

Tomasz Kalinowski

tfprobability

Interface to 'TensorFlow Probability'

Sigrid Keydana

Daniel Falbel

Kevin Kuo

RStudio 

vi_triangular function

<dl><dt>logu</dt>
<dd><code>float</code>-like <code>Tensor</code> representing <code>log(u)</code> from above.</dd>
<dt>name</dt>
<dd>name prefixed to Ops created by this function.</dd></dl>

Arguments

The Triangular Csiszar-function in log-space — vi_triangular

<dl>

<dt>logu</dt>
<dd><code>float</code>-like <code>Tensor</code> representing <code>log(u)</code> from above.</dd>


<dt>name</dt>
<dd>name prefixed to Ops created by this function.</dd>

</dl>

vi_triangular: The Triangular Csiszar-function in log-space

Description

Usage

Value

Arguments

Details

See Also