new base class: UnScaledPESModel
#8
Merged
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
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #8 +/- ##
==========================================
- Coverage 88.77% 88.00% -0.78%
==========================================
Files 33 35 +2
Lines 1916 1968 +52
==========================================
+ Hits 1701 1732 +31
- Misses 215 236 +21 ☔ View full report in Codecov by Sentry. |
jla-gardner
changed the title
UnScaledPESModel
Merged
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
All$E = \sum_i \varepsilon_i$ .
GraphPESModels make generate total energy predictions as a sum over local contributions:NN models tend to work best when they are trained to predict raw outputs that are unit-normally distributed:$y \sim \mathcal{N}(0, 1)$ . It therefore "makes sense" to introduce this base class that guesses the variance in local energy contribution per element during pre-fitting, and then uses these (learnable) values to scale raw NN outputs to live on the same scale as the energies they are trying to predict.