Gradient of latent space variable in Turing?

General Usage
2

The code generated by the logprob macro is not AD friendly. Try the function:

Turing.gradient_logp(Turing.ZygoteAD(), θ, Turing.VarInfo(model), model)

but you need to define the model using MyModel(x) and θ should be the vector of random variables in order of appearance in the model. In this case, it is just [σ].

3 Likes