pymc.Approximation.set_size_and_deterministic#

Approximation.set_size_and_deterministic(node, s, d, more_replacements=None)[source]#

Dev - after node is sampled via symbolic_sample_over_posterior() or symbolic_single_sample() new random generator can be allocated and applied to node

Parameters:
node: :class:`Variable`

PyTensor node with symbolically applied VI replacements

s: scalar

desired number of samples

d: bool or int

whether sampling is done deterministically

more_replacements: dict

more replacements to apply

Returns:
Variable with applied replacements, ready to use