Symbolic Regression with a Learned Concept Library

Autor:	Grayeli, Arya, Sehgal, Atharva, Costilla-Reyes, Omar, Cranmer, Miles, Chaudhuri, Swarat
Rok vydání:	2024
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence Computer Science - Neural and Evolutionary Computing Computer Science - Symbolic Computation
Druh dokumentu:	Working Paper
Popis:	We present a novel method for symbolic regression (SR), the task of searching for compact programmatic hypotheses that best explain a dataset. The problem is commonly solved using genetic algorithms; we show that we can enhance such methods by inducing a library of abstract textual concepts. Our algorithm, called LaSR, uses zero-shot queries to a large language model (LLM) to discover and evolve concepts occurring in known high-performing hypotheses. We discover new hypotheses using a mix of standard evolutionary steps and LLM-guided steps (obtained through zero-shot LLM queries) conditioned on discovered concepts. Once discovered, hypotheses are used in a new round of concept abstraction and evolution. We validate LaSR on the Feynman equations, a popular SR benchmark, as well as a set of synthetic tasks. On these benchmarks, LaSR substantially outperforms a variety of state-of-the-art SR approaches based on deep learning and evolutionary algorithms. Moreover, we show that LaSR can be used to discover a novel and powerful scaling law for LLMs. Comment: preprint version; 10 pages
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2409.09359 Zobrazit plný text záznamu View this record from Arxiv