tfp.edward2.LogitNormal

View source on GitHub

Create a random variable for LogitNormal.

See LogitNormal for more details.

RandomVariable.

Original Docstring for Distribution

Construct a logit-normal distribution.

The LogititNormal distribution models positive-valued random variables whose logit (i.e., sigmoid_inverse, i.e., log(p) - log1p(-p)) is normally distributed with mean loc and standard deviation scale. It is constructed as the sigmoid transformation, (i.e., 1 / (1 + exp(-x))) of a Normal distribution.

loc Floating-point Tensor; the mean of the underlying Normal distribution(s). Must broadcast with scale.
scale Floating-point Tensor; the stddev of the underlying Normal distribution(s). Must broadcast with loc.
validate_args Python bool, default False. Whether to validate input with asserts. If validate_args is False, and the inputs are invalid, correct behavior is not guaranteed.
allow_nan_stats Python bool, default True. If False, raise an exception if a statistic (e.g. mean/mode/etc...) is undefined for any batch member If True, batch members with valid parameters leading to undefined statistics will return NaN for this statistic.
name The name to give Ops created by the initializer.