|View source on GitHub|
Create a random variable for GeneralizedPareto.
tfp.edward2.GeneralizedPareto( *args, **kwargs )
See GeneralizedPareto for more details.
Original Docstring for Distribution
Construct a Generalized Pareto distribution.
loc: The location / shift of the distribution. GeneralizedPareto is a location-scale distribution. This parameter lower bounds the distribution's support. Must broadcast with
concentration. Floating point
scale: The scale of the distribution. GeneralizedPareto is a location-scale distribution, so doubling the
scaledoubles a sample and halves the density. Strictly positive floating point
Tensor. Must broadcast with
concentration: The shape parameter of the distribution. The larger the magnitude, the more the distribution concentrates near
concentration >= 0) or near
loc - (scale/concentration)(for
concentration < 0). Floating point
Truedistribution parameters are checked for validity despite possibly degrading runtime performance. When
Falseinvalid inputs may silently render incorrect outputs.
True, statistics (e.g., mean, variance) use the value "
NaN" to indicate the result is undefined. When
False, an exception is raised if one or more of the statistic's batch members are undefined.
strname prefixed to Ops created by this class.
concentrationhave different dtypes.