This repository has been archived by the owner on Aug 18, 2023. It is now read-only.
Log partition function improvements #167
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* try updating * update python versions * Tests passing * increase tolerance for flaky test * update setup.py
zaqqwerty
changed the title
|
Superceded by #180 |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Adds a default log partition function estimator and derivative estimator.
Part of #140. Estimating the QMHL loss requires estimating the log partition function. Equation C1 in the appendix provides a sample-based approximation to it. Here I implemented this approximation in the base
EnergyInferenceclass.More importantly, estimating the derivative of the QMHL loss requires estimating the derivative of the log partition function. Luckily this quantity is more well behaved than the log partition itself: an estimator is provided in equation C2 of the appendix. This is implemented as the default for the
EnergyInferenceclass.