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
Could we split up estimate_parameters to have a "profiling only" option? We have a "barrier only" option via profile_P = FALSE, but not the converse.
Motivation -- I have a dataset where I have my barrier method has converged, but is getting stuck/slow on profiling. I'd love to rerun it without waiting for the barrier steps to rerun.
Note -- this shouldn't be hard, just takes some careful checking. One issue is that the addition to move to the interior of the simplex, which happens first, needs to go into the barrier section.
The text was updated successfully, but these errors were encountered:
Could we split up
estimate_parameters
to have a "profiling only" option? We have a "barrier only" option viaprofile_P = FALSE
, but not the converse.Motivation -- I have a dataset where I have my barrier method has converged, but is getting stuck/slow on profiling. I'd love to rerun it without waiting for the barrier steps to rerun.
Note -- this shouldn't be hard, just takes some careful checking. One issue is that the addition to move to the interior of the simplex, which happens first, needs to go into the barrier section.
The text was updated successfully, but these errors were encountered: