SymbolicGPT: A Generative Transformer Model for Symbolic Regression

TL;DR

SymbolicGPT is a transformer-based model designed for symbolic regression, demonstrating improved accuracy, efficiency, and flexibility over traditional methods through extensive experiments.

Contribution

This work introduces SymbolicGPT, a novel transformer model tailored for symbolic regression, leveraging language modeling techniques to enhance performance and data efficiency.

Findings

Outperforms competing models in accuracy

Reduces running time for symbolic regression tasks

Shows strong data efficiency in experiments

Abstract

Symbolic regression is the task of identifying a mathematical expression that best fits a provided dataset of input and output values. Due to the richness of the space of mathematical expressions, symbolic regression is generally a challenging problem. While conventional approaches based on genetic evolution algorithms have been used for decades, deep learning-based methods are relatively new and an active research area. In this work, we present SymbolicGPT, a novel transformer-based language model for symbolic regression. This model exploits the advantages of probabilistic language models like GPT, including strength in performance and flexibility. Through comprehensive experiments, we show that our model performs strongly compared to competing models with respect to the accuracy, running time, and data efficiency.