Rename LLaMEA-SAGE to LLaMEA-CFG throughout codebase - #164
Conversation
…ebooks Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_019V1NLKXdLGQgRWRDJMLAmx
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 053ca999fc
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| ], | ||
| "source": [ | ||
| "fig = plot_speedup(logger, method_fast=\"LLaMEA-SAGE\", method_slow=\"LLaMEA\", save=False, return_fig=True, budget=200, replace_labels={'ES': 'LLaMEA', 'ES-guided': 'LLaMEA-SAGE'})\n", | ||
| "fig = plot_speedup(logger, method_fast=\"LLaMEA-CFG\", method_slow=\"LLaMEA\", save=False, return_fig=True, budget=200, replace_labels={'ES': 'LLaMEA', 'ES-guided': 'LLaMEA-CFG'})\n", |
There was a problem hiding this comment.
When this notebook is run against the bundled paper_results/MABBOB_guided* logs, the raw methods are still ES, ES-guided, LLaMEA, LLaMEA-SAGE, LHNS:vns, and MCTS_AHD; there is no raw LLaMEA-CFG entry. plot_speedup validates method_fast against logger.get_methods_problems() before applying replace_labels, so this renamed lookup now raises ValueError and stops generation of MABBOB-speedup.png rather than just changing the displayed label. Keep the lookup key as LLaMEA-SAGE (or rename/map the archived logs before the existence check) and use LLaMEA-CFG only as the display label.
Useful? React with 👍 / 👎.
2 participants
Summary
This PR renames the method variant "LLaMEA-SAGE" to "LLaMEA-CFG" (Context-aware Feature Guidance) across all experiment scripts, notebooks, and visualization code. This is a straightforward nomenclature update to reflect the method's actual design approach.
Key Changes
run_archive_guided.py,run_archive_guided-2.py,run_archive_guided-3.py): Updated method instantiation names from"LLaMEA-SAGE"to"LLaMEA-CFG"visualize_1.ipynb,visualize_2.ipynb,visualize_3.ipynb): Updated all label mappings, method lists, and plot titles to use the new namefinal_validation.ipynb): Updated label transformations in legend handling codeiohblade/plots.py): Updated method title mapping inplot_experiment_CEG()functionREADME.md): Updated project title and experiment descriptions to reference the new nameexamples/visualize_kerneltuner.ipynb): Updated commented-out label replacement codeImplementation Details
All changes maintain consistency across:
No functional changes to the algorithm or its behavior—this is purely a naming update for clarity and consistency.
https://claude.ai/code/session_019V1NLKXdLGQgRWRDJMLAmx