SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.09359 · NeurIPS · 2024

Symbolic Regression with a Learned Concept Library

Miles Cranmer, U Austin, Swarat Chaudhuri, Atharva Sehgal, Arya Grayeli, Omar Costilla, Reyes Mit

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 abstract 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 new and powerful scaling law for LLMs.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2409.09359")
get_code_for_paper("2409.09359")
have("2409.09359")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2409.09359.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2409.09359.svg)](https://syntology.ai/paper/2409.09359)

Connect an agent — have() is free.