Skip to content
This repository was archived by the owner on Apr 24, 2024. It is now read-only.

Improvements to Ridge#11

Merged
DavideTisi merged 1 commit intomainfrom
ridge_impros
Feb 15, 2023
Merged

Improvements to Ridge#11
DavideTisi merged 1 commit intomainfrom
ridge_impros

Conversation

@PicoCentauri
Copy link
Collaborator

This PR is factoring out the improvements to Ridge started in #10. It contains the following changes.

  • Move alpha and rcond into fit method
  • Rename coef attribute to weights to be consistent with documentation.
  • Allow floats in addition to a TensorMap as alpha parameter
  • Various improvements to the docstring and example

* Move `alpha` and `rcond` into fit method
* Allow floats in addition to a TensorMap as `alpha` parameter
* Various improvements to the docstring and example
@DavideTisi DavideTisi merged commit 143c095 into main Feb 15, 2023
@DavideTisi DavideTisi deleted the ridge_impros branch February 15, 2023 13:43
# ``"positions"`` (forces).


clf = Ridge(parameter_keys=["values", "positions"])
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Quick question: this parameter_keys is here to allow training of a model using only gradients, right? otherwise it feels a bit redundant: one could say we use everything defined on the input tensormap

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants