You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Add a new argument to optimization methods to allow inclusion of Jacobian in order to produce the maximum a posteriori (MAP) estimate in addition to the existing penalized maximum likelihood estimate.
Description:
Add a new argument
jacobian: boolean valued, default false, indicating whether to include Jacobian in log density target
Expected Output:
This is testable with a constrained parameter that induces a Jacobian adjustment. A simple one like a single positive-constrained value is easy to test.
Other information
This will have to be staged after an upgrade to optimization service functions in Stan, which in turn require an update to the optimization functions.
Current Version:
v2.30.1
The text was updated successfully, but these errors were encountered:
Summary:
Add a new argument to optimization methods to allow inclusion of Jacobian in order to produce the maximum a posteriori (MAP) estimate in addition to the existing penalized maximum likelihood estimate.
Description:
Add a new argument
jacobian
: boolean valued, defaultfalse
, indicating whether to include Jacobian in log density targetExpected Output:
This is testable with a constrained parameter that induces a Jacobian adjustment. A simple one like a single positive-constrained value is easy to test.
Other information
This will have to be staged after an upgrade to optimization service functions in Stan, which in turn require an update to the optimization functions.
Current Version:
v2.30.1
The text was updated successfully, but these errors were encountered: