-
Notifications
You must be signed in to change notification settings - Fork 34
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Recreate Multinest in Pints #282
Comments
Note to self: add in importance nested sampling as an option. See: https://arxiv.org/pdf/1306.2144.pdf |
Current notebook is here: https://github.com/pints-team/pints/blob/master/studies/multinest.ipynb (in master), as suggested in #480 |
For an alternative plan of adding a wrapper to existing software, see #161 |
Have now recapitulated ellipsoidal results from paper (see f42dad0) |
Am adding to project for PINTS paper as nearly done. |
- added getter for ellipsoidtree - corrected pseudocode to be more representative of actual approach - added enlargement factor capacity - made ellipsoid gap used - corrected hyperparameters
- also added max number of tries for while loop for kmeans addresses #282
- Error handling for singular matrix issue when forming bounding ellipse - Added back in recursion as it was used in the Matlab implementation we were following - Cleaned up the notebook and removed the logistic example as Goodwin is better - Improved docstrings for algo pseudocode Addresses #282
PR: #1319 |
Again to avoid dependency issues it should be possible (and informative) to recreate the Multinest sampling algorithm in Pints. See here.
The text was updated successfully, but these errors were encountered: