|View source on GitHub|
Create a random variable for StudentTProcess.
tfp.edward2.StudentTProcess( *args, **kwargs )
See StudentTProcess for more details.
Original Docstring for Distribution
Instantiate a StudentTProcess Distribution.
df: Positive Floating-point
Tensorrepresenting the degrees of freedom. Must be greater than 2.
PositiveSemidefiniteKernel-like instance representing the TP's covariance function.
Tensorrepresenting finite (batch of) vector(s) of points in the index set over which the TP is defined. Shape has the form
[b1, ..., bB, e, f1, ..., fF]where
Fis the number of feature dimensions and must equal
eis the number (size) of index points in each batch. Ultimately this distribution corresponds to a
e-dimensional multivariate Student's T. The batch shape must be broadcastable with
kernel.batch_shapeand any batch dims yielded by
callablethat acts on
index_pointsto produce a (batch of) vector(s) of mean values at
index_points. Takes a
[b1, ..., bB, f1, ..., fF]and returns a
Tensorwhose shape is broadcastable with
[b1, ..., bB]. Default value:
Noneimplies constant zero function.
Tensoradded to the diagonal of the covariance matrix to ensure positive definiteness of the covariance matrix. Default value:
Truedistribution parameters are checked for validity despite possibly degrading runtime performance. When
Falseinvalid inputs may silently render incorrect outputs. Default value:
True, statistics (e.g., mean, mode, 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. Default value:
strname prefixed to Ops created by this class. Default value: "StudentTProcess".
Noneand is not callable.