pymc icon indicating copy to clipboard operation
pymc copied to clipboard

Incorporate AePPL into GaussianRandomWalk

Open larryshamalama opened this issue 3 years ago • 0 comments

A recent PR #5298 added GaussianRandomWalk distribution to v4. It would be possible to use AePPL to obtain the Aesara graph corresponding to desired rv_op and retrieve the correct log-probability graph. The use of AePPL here would be desirable as we will no longer need to implement a corresponding RandomVariable class nor implement the logp method. Moreover, it would generalize the random walk to make use of non-Gaussian distributions.

cc @ricardoV94

larryshamalama avatar May 14 '22 15:05 larryshamalama