Researchers have introduced DIGEST, a novel method for symbolic regression that combines Large Language Models (LLMs) with Genetic Programming (GP). DIGEST addresses limitations in current approaches by using an LLM-derived policy to seed GP populations, enhancing generation flexibility. It also incorporates a feedback loop where high-quality expressions discovered by GP are used to update the LLM policy, enabling it to learn from past search discoveries. Experiments demonstrate DIGEST's superior performance in recovering ground-truth expressions and its efficiency compared to existing methods. AI
IMPACT This method could improve the discovery of scientific expressions from data, potentially accelerating research in scientific domains.
RANK_REASON The cluster contains a research paper detailing a new method for symbolic regression. [lever_c_demoted from research: ic=1 ai=1.0]
- alphaXiv
- arXiv
- CatalyzeX
- DagsHub
- DIGEST
- Genetic Programming
- Gotit.pub
- Hugging Face
- IArxiv
- LLM
- ScienceCast
- Symbolic Regression
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
