Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients

Abstract

Discovering the underlying mathematical expressions describing a dataset is a core challenge for artificial intelligence. This is the problem of $\text{symbolic regression}$. Despite recent advances in training neural networks to solve complex tasks, deep learning approaches to symbolic regression are underexplored. We propose a framework that leverages deep learning for symbolic regression via a simple idea: use a large model to search the space of small models. Specifically, we use a recurrent neural network to emit a distribution over tractable mathematical expressions and employ a novel risk-seeking policy gradient to train the network to generate better-fitting expressions. Our algorithm outperforms several baseline methods (including Eureqa, the gold standard for symbolic regression) in its ability to exactly recover symbolic expressions on a series of benchmark problems, both with and without added noise. More broadly, our contributions include a framework that can be applied to optimize hierarchical, variable-length objects under a black-box performance metric, with the ability to incorporate constraints in situ, and a risk-seeking policy gradient formulation that optimizes for best-case performance instead of expected performance.

Published at International Conference on Learning Representations, 2021

References in corpus (10)

• Neural Architecture Search with Reinforcement Learning
• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• WaveNet: A Generative Model for Raw Audio
• Searching for Activation Functions
• GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
• Neural Optimizer Search with Reinforcement Learning
• EPOpt: Learning Robust Neural Network Policies Using Model Ensembles
• Bayesian Symbolic Regression
• Learning Equations for Extrapolation and Control
• Neural Program Synthesis with Priority Queue Training

Cited by in corpus (6)

• Shape-constrained Symbolic Regression -- Improving Extrapolation with Prior Knowledge
• SymbolicGPT: A Generative Transformer Model for Symbolic Regression
• Discovering explicit Reynolds-averaged turbulence closures for turbulent separated flows through deep learning-based symbolic regression with non-linear corrections
• Efficient Generator of Mathematical Expressions for Symbolic Regression
• Informed Equation Learning
• CTSR: Cartesian tensor-based sparse regression for data-driven discovery of high-dimensional invariant governing equations