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
I noticed TSEMO is not performing perfectly, and I think the issue is that I am missing two things in the implementation:
Selecting the reference for hypervolume improvement calculations as the anti-ideal point
Spectral sampling of the GP, which gives an analytic function approximator to the posterior. (see here and the original TSEMO paper) I'm not really sure how much of a difference this makes.
Also, I should do a comparison to the Matlab version on the same problems.
The text was updated successfully, but these errors were encountered:
I noticed TSEMO is not performing perfectly, and I think the issue is that I am missing two things in the implementation:
Also, I should do a comparison to the Matlab version on the same problems.
The text was updated successfully, but these errors were encountered: