A Neural-Guided Dynamic Symbolic Network for Exploring Mathematical Expressions from Data

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Wenqiang, Li, Weijun, Yu, Lina, Wu, Min, Sun, Linjun, Liu, Jingyi, Li, Yanjie, Wei, Shu, Deng, Yusong, Hao, Meilan
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910466445410304
author Li, Wenqiang
Li, Weijun
Yu, Lina
Wu, Min
Sun, Linjun
Liu, Jingyi
Li, Yanjie
Wei, Shu
Deng, Yusong
Hao, Meilan
author_facet Li, Wenqiang
Li, Weijun
Yu, Lina
Wu, Min
Sun, Linjun
Liu, Jingyi
Li, Yanjie
Wei, Shu
Deng, Yusong
Hao, Meilan
contents Symbolic regression (SR) is a powerful technique for discovering the underlying mathematical expressions from observed data. Inspired by the success of deep learning, recent deep generative SR methods have shown promising results. However, these methods face difficulties in processing high-dimensional problems and learning constants due to the large search space, and they don't scale well to unseen problems. In this work, we propose DySymNet, a novel neural-guided Dynamic Symbolic Network for SR. Instead of searching for expressions within a large search space, we explore symbolic networks with various structures, guided by reinforcement learning, and optimize them to identify expressions that better-fitting the data. Based on extensive numerical experiments on low-dimensional public standard benchmarks and the well-known SRBench with more variables, DySymNet shows clear superiority over several representative baseline models. Open source code is available at https://github.com/AILWQ/DySymNet.
format Preprint
id arxiv_https___arxiv_org_abs_2309_13705
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A Neural-Guided Dynamic Symbolic Network for Exploring Mathematical Expressions from Data
Li, Wenqiang
Li, Weijun
Yu, Lina
Wu, Min
Sun, Linjun
Liu, Jingyi
Li, Yanjie
Wei, Shu
Deng, Yusong
Hao, Meilan
Machine Learning
Artificial Intelligence
Symbolic regression (SR) is a powerful technique for discovering the underlying mathematical expressions from observed data. Inspired by the success of deep learning, recent deep generative SR methods have shown promising results. However, these methods face difficulties in processing high-dimensional problems and learning constants due to the large search space, and they don't scale well to unseen problems. In this work, we propose DySymNet, a novel neural-guided Dynamic Symbolic Network for SR. Instead of searching for expressions within a large search space, we explore symbolic networks with various structures, guided by reinforcement learning, and optimize them to identify expressions that better-fitting the data. Based on extensive numerical experiments on low-dimensional public standard benchmarks and the well-known SRBench with more variables, DySymNet shows clear superiority over several representative baseline models. Open source code is available at https://github.com/AILWQ/DySymNet.
title A Neural-Guided Dynamic Symbolic Network for Exploring Mathematical Expressions from Data
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2309.13705