OMEGA自动生成优于传统方法的机器学习算法。
OMEGA: Optimizing Machine Learning by Evaluating Generated Algorithms
- 用结构化提示词生成新算法思路，自动转为可执行代码。
- 在20个基准数据集上性能超越scikit-learn基线。
- 适合想快速探索新算法的研究者与开发者。
为实现人工智能研究的自动化，我们提出端到端框架OMEGA：通过评估生成的算法优化机器学习。该系统从想法生成开始，最终输出可执行代码。通过结合结构化元提示工程与可执行代码生成，OMEGA创建了多个新型机器学习分类器。在20个基准数据集（infinity-bench）上的测试表明，这些算法性能均优于scikit-learn基线。本文讨论的模型及更多算法可通过Python包安装：pip install omega-models。
原文摘要 · Abstract (English)
In order to automate AI research we introduce a full, end-to-end framework, OMEGA: Optimizing Machine learning by Evaluating Generated Algorithms, that starts at idea generation and ends with executable code. Our system combines structured meta-prompt engineering with executable code generation to create new ML classifiers. The OMEGA framework has been utilized to generate several novel algorithms that outperform scikit-learn baselines across a robust selection of 20 benchmark datasets (infinity-bench). You can access models discussed in this paper and more in the python package: pip install omega-models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。