Create a random variable for MultivariateNormalLinearOperator.
tfp.edward2.MultivariateNormalLinearOperator( *args, **kwargs )
See MultivariateNormalLinearOperator for more details.
Original Docstring for Distribution
Construct Multivariate Normal distribution on
batch_shape is the broadcast shape between
event_shape is given by last dimension of the matrix implied by
scale. The last dimension of
loc (if provided) must broadcast with this.
covariance = scale @ scale.T.
Additional leading dimensions (if any) will index batches.
Tensor. If this is set to
0. When specified, may have shape
[B1, ..., Bb, k]where
b >= 0and
kis the event size.
scale: Instance of
[B1, ..., Bb, k, k].
False. Whether to validate input with asserts. If
False, and the inputs are invalid, correct behavior is not guaranteed.
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.
TypeError: if not