Added multi-modal posterior exampler #9
Conversation
A multi-modal posterior constructed from a Gaussian Mixture Model fit to the posteriors sampler from the AEM example. Provides a test case for examining performance of the automatic pseudo-prior on a complex synthetic example with prescribed posterior weights over states..
Welcome to Codecov 🎉Once you merge this PR into your default branch, you're all set! Codecov will compare coverage reports and display results in all future pull requests. Thanks for integrating Codecov - We've got you covered ☂️ |
|
@JuergHauser Could you look at this. I created a new example for pytransC which uses a multi-modal synthetic posterior PDF in up to 19 dimensions. It is built from AEM example but details are designed to be invisible. The log_posterior function is fast and represents a complex multi-modal posterior where evidence values for each state can be set to any values in code. Trans-C state-jump sampler is demonstrated. It is meant to be a demonstration of the success of the auto-build-pseudo-prior routine, which create a low order GMM from posterior samples. It is parallelized and Trans-C recovers the known evidence values reasonably well. Could you please review code for any issues. Edit as you see fit. |
|
Looking good to me - will merge... |
A multi-modal posterior constructed from a Gaussian Mixture Model fit to the posteriors sampler from the AEM example. Provides a test case for examining performance of the automatic pseudo-prior on a complex synthetic example with prescribed posterior weights over states..