Patch bfgs upper bound #399
Open
MaxenceGollier wants to merge 2 commits intoJuliaSmoothOptimizers:mainfrom
Open
Patch bfgs upper bound #399MaxenceGollier wants to merge 2 commits intoJuliaSmoothOptimizers:mainfrom
MaxenceGollier wants to merge 2 commits intoJuliaSmoothOptimizers:mainfrom
Conversation
Contributor
Author
|
Can we merge @dpo ? Test aren't failing due to this modification. |
There was a problem hiding this comment.
Pull request overview
This PR fixes the computation of the stored upper bound on the forward L-BFGS operator norm, aligning the update with the stated bound formula in LBFGSData and preventing underestimated bounds that can break downstream checks (as seen in RegularizedOptimization.jl runs).
Changes:
- Update
opnorm_upper_boundmaintenance to add/subtract‖bᵢ‖²(squared norms) instead of‖bᵢ‖. - Keep the bound consistent with the documented inequality
‖Bₖ‖₂ ≤ ‖B₀‖₂ + ∑ᵢ ‖bᵢ‖₂².
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Following these runs: https://github.com/JuliaSmoothOptimizers/RegularizedOptimization.jl/actions/runs/21675732671
There is a mistake with how we compute the upper bound. With this patch, tests complete in
RegularizedOptimization.jlat least locally.@dpo, if you agree, please merge.