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

Separate out Matern kernels #835

Merged
merged 7 commits into from
Oct 23, 2024
Merged

Separate out Matern kernels #835

merged 7 commits into from
Oct 23, 2024

Conversation

sbfnk
Copy link
Contributor

@sbfnk sbfnk commented Oct 18, 2024

Description

This PR closes #760 and #828.

It splits out spectral densities of Matern Kernels of order 1/2, 3/2 and 5/2.

It would be good for someone to check both the maths (which I've updated in the vignette) and code are correct.

Initial submission checklist

  • My PR is based on a package issue and I have explicitly linked it.
  • I have tested my changes locally (using devtools::test() and devtools::check()).
  • I have added or updated unit tests where necessary.
  • I have updated the documentation if required and rebuilt docs if yes (using devtools::document()).
  • I have followed the established coding standards (and checked using lintr::lint_package()).
  • I have added a news item linked to this PR.

After the initial Pull Request

  • I have reviewed Checks for this PR and addressed any issues as far as I am able.

Copy link
Contributor

This is how benchmark results would change (along with a 95% confidence interval in relative change) if 8db04a5 is merged into main:

  • ✔️default: 22.9s -> 23.1s [-12.64%, +14.1%]
  • ✔️no_delays: 28.2s -> 29.2s [-6.41%, +13.73%]
  • ✔️random_walk: 10.2s -> 9.95s [-7.91%, +3.37%]
  • ✔️stationary: 22s -> 7.31s [-146.77%, +13.19%]
  • ✔️uncertain: 38.6s -> 39s [-8.36%, +10.75%]
    Further explanation regarding interpretation and methodology can be found in the documentation.

@sbfnk sbfnk linked an issue Oct 18, 2024 that may be closed by this pull request
Copy link
Contributor

This is how benchmark results would change (along with a 95% confidence interval in relative change) if 3e43cdb is merged into main:

  • 🚀default: 23.3s -> 20.2s [-24.81%, -1.84%]
  • ✔️no_delays: 28.3s -> 26.8s [-13.05%, +2.86%]
  • ✔️random_walk: 10s -> 9.82s [-7.49%, +3.81%]
  • ✔️stationary: 13s -> 13.7s [-16.99%, +27.53%]
  • ✔️uncertain: 38.2s -> 51.7s [-46.64%, +116.91%]
    Further explanation regarding interpretation and methodology can be found in the documentation.

NEWS.md Outdated Show resolved Hide resolved
seabbs
seabbs previously approved these changes Oct 23, 2024
Copy link
Contributor

@seabbs seabbs left a comment

Choose a reason for hiding this comment

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

This looks right to me based but I also convinced myself the other approach was correct so take that with a pinch of salt.

Co-authored-by: Sam Abbott <s.e.abbott12@gmail.com>
@sbfnk sbfnk requested a review from seabbs October 23, 2024 10:38
Copy link
Contributor

This is how benchmark results would change (along with a 95% confidence interval in relative change) if f8228d0 is merged into main:

  • ✔️default: 23.6s -> 24.3s [-8.87%, +14.41%]
  • ✔️no_delays: 26.9s -> 28.7s [-3.93%, +17.11%]
  • ✔️random_walk: 9.61s -> 10.1s [-1.32%, +11.29%]
  • ✔️stationary: 14s -> 12.6s [-26.8%, +6.8%]
  • ✔️uncertain: 36.5s -> 36.1s [-9.92%, +7.7%]
    Further explanation regarding interpretation and methodology can be found in the documentation.

@sbfnk sbfnk added this pull request to the merge queue Oct 23, 2024
Merged via the queue into main with commit 3adc6ab Oct 23, 2024
15 checks passed
@sbfnk sbfnk deleted the separate-kernels branch October 23, 2024 16:11
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.

spectral densities of Matern Kernels of order != 3/2 Optimised Matern kernels
2 participants