-
Notifications
You must be signed in to change notification settings - Fork 47
Adding Metropolis-Adjusted Langevin Algorithm #1617
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
base: develop
Are you sure you want to change the base?
Conversation
|
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## develop #1617 +/- ##
===========================================
- Coverage 84.37% 84.36% -0.01%
===========================================
Files 164 165 +1
Lines 14320 14395 +75
===========================================
+ Hits 12082 12145 +63
- Misses 2238 2250 +12 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
Co-authored-by: Daniel Weindl <[email protected]>
Co-authored-by: Daniel Weindl <[email protected]>
PaulJonasJost
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Awesome, looks good to me, thanks :)
|
@dilpath, this is ready to merge I think |
This pull request introduces a new gradient-based sampler, the Metropolis-Adjusted Langevin Algorithm (MALA), to the
pypesto.samplemodule, and refactors the covariance regularization in the adaptive Metropolis sampler. The changes also enhance the test suite and documentation to demonstrate and validate the new functionality.I refactored the covariance regularization to return both the Cholesky decomposition and the regularized covariance matrix, improving numerical stability. The regularization function now supports multiple attempts and safe fallback strategies. Before it could happen that adaptive MCMC just fails at some point due to an ill-conditioned proposal covariance.