Skip to content
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

weighted least squares -> ace-experiments #52

Merged
merged 25 commits into from
Sep 8, 2023

Conversation

emmanuellujan
Copy link
Member

No description provided.

joannajzou and others added 25 commits April 7, 2023 19:29
Add additional method to learn! which gives a linear least squares solution to a UnivariateLinearProblem and CovariateLinearProblem with known noise variance (weights).

This function still needs to be tested, which will be done in a future commit.
Julia does not support multiple dispatch on keyword arguments, so in the new method for learn!(), the variable "var" must be defined as a Vector of variance parameters for each data point. 

The line copy!(lb.beta, linear_problem.beta) is removed because it is redundant.
Standardizing naming convention for files under test directory
bring changes on clean-up-refactor into weighted-least-squares
I had previously (mistakenly) removed the line "copy!(lb.β, linear_problem.β)" thinking it was redundant, but it is necessary for copying the learned value of β from linear_problem::LinearProblem to lb::LinearBasisPotential.
Tests the learn!() function for linear problems in Learning/linear.jl. At this stage, it only tests the types/values of elements of a UnivariateLinearProblem.
Start to draft CovariateLinearProblem testes
@emmanuellujan emmanuellujan merged commit 33393cb into ace-experiments Sep 8, 2023
4 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants