Summary:
Currently the mean is saved in the CSV output above the samples, but there is no way to get the estimated (co-)variance out, short of approximating it through the samples.
We could save it to JSON, similar to issues #3181 #3260
Description:
Option to save the non-mean parameters of the family for ADVI. For meanfield this is
|
* Log standard deviation (log scale) vector. |
|
*/ |
|
Eigen::VectorXd omega_; |
For fullrank this is
|
* Cholesky factor of covariance: |
|
* Sigma = L_chol * L_chol.transpose() |
|
*/ |
|
Eigen::MatrixXd L_chol_; |
These could be used to e.g. draw further samples from the approximation from outside the algorithmic run.
Additional Information:
Originally requested on the forums here: https://discourse.mc-stan.org/t/cmdstanpy-variational-how-to-get-density-parameters/37280/
Current Version:
v2.35.0
Summary:
Currently the mean is saved in the CSV output above the samples, but there is no way to get the estimated (co-)variance out, short of approximating it through the samples.
We could save it to JSON, similar to issues #3181 #3260
Description:
Option to save the non-mean parameters of the family for ADVI. For meanfield this is
stan/src/stan/variational/families/normal_meanfield.hpp
Lines 28 to 30 in 9de06d4
For fullrank this is
stan/src/stan/variational/families/normal_fullrank.hpp
Lines 28 to 31 in 9de06d4
These could be used to e.g. draw further samples from the approximation from outside the algorithmic run.
Additional Information:
Originally requested on the forums here: https://discourse.mc-stan.org/t/cmdstanpy-variational-how-to-get-density-parameters/37280/
Current Version:
v2.35.0