refactor: migrate least-squares fits to basin 1.11 - #34
Merged
Merged
Conversation
Upgrade `basin` to 1.11 and replace `levenberg-marquardt` across calibration, volatility surfaces, and AI surrogates. Preserve evaluation budgets and report the best accepted fit on failures. Add convergence fixtures and Criterion comparisons. Use bounded CGMYSV coordinates to retain convergence, preserve negative-sigma SVI fits, and remove unused BSM history allocations. The measured fits retain their accuracy. Six benchmark cases improve, Heston stays within noise, and variance gamma remains about 3% slower. Closes rust-dd#33
|
@jolars is attempting to deploy a commit to the GymPiper Team on Vercel. A member of the Team first needs to authorize it. |
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Replace
levenberg-marquardtwith basin 1.11 across calibration, volatility surfaces, and AI surrogates. This also adds bounded coordinates to keep CGMYSV converging, preserves SVI fits with negative sigma, and removes unused BSM history allocations.Criterion means from release builds, with 20 samples per case:
Both Heston changes are within noise. Variance gamma is consistently a little slower, with the same fit accuracy and evaluation count.
No convergence regression appeared in the test fixtures. Calibration, surface, stats, and AI tests passed, as did workspace/Python checks and the benchmark build. Scoped Clippy passed; strict checks still hit existing warnings. The all-features Clippy commit hook was skipped because it pulls in Apple frameworks on Linux.
I used Codex GPT-6 Astra to prepare this PR.