Classes and helper functions for creating Stochastic Tensors.
StochasticTensor objects wrap
Distribution objects. Their
values may be samples from the underlying distribution, or the distribution
mean (as governed by
value_type). These objects provide a
method for use when sampling from a non-reparameterized distribution.
lossmethod is used in conjunction with
to produce a single differentiable loss in stochastic graphs having
both continuous and discrete stochastic nodes.
Stochastic Tensor Classes