> Why do you think similar approaches never landed on jax?
Isn't this just adding noise to some branching conditions? What would take for a framework like Jax to "support" it, it seems like all you have to do is change
> if (x>0)
to
> if (x+n > 0)
where n is a sampled Gaussian.
Not sure this warrants any kind of changes in a framework if it's truly that trivial.
Semantically it seems truly that trivial, but in practice handling expectations in AD requires some additional machinery not found in implementations that were not written for nondeterminism.
Isn't this just adding noise to some branching conditions? What would take for a framework like Jax to "support" it, it seems like all you have to do is change
> if (x>0)
to
> if (x+n > 0)
where n is a sampled Gaussian.
Not sure this warrants any kind of changes in a framework if it's truly that trivial.