Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients
read the original abstract
Discovering the underlying mathematical expressions describing a dataset is a core challenge for artificial intelligence. This is the problem of $\textit{symbolic regression}$. 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.
This paper has not been read by Pith yet.
Forward citations
Cited by 23 Pith papers
-
Sample Complexity of Scientific Discovery: PAC Learnability of Compositional Function Trees
Proves that Rademacher complexity of depth-d compositional trees over finite operator vocabulary is controlled by (K b L)^{d} / sqrt(n) under Lipschitz conditions on operators.
-
FunctionEvolve: Structure-Guided Symbolic Regression with LLMs
FunctionEvolve recovers 107 exact symbolic forms out of 129 synthetic tasks (82.9% SA@50) by using expression-tree structure for evolutionary search, parent selection, mutation, and coefficient scoring with LLMs.
-
Symbolic Regression via Latent Iterative Refinement
LEE performs iterative amortized inference in a functionally grounded latent space to produce 2-10x simpler symbolic expressions than strong baselines on SRBench.
-
Learning First Integrals via Backward-Generated Data and Guided Reinforcement Learning
FISolver trains a compact LLM on backward-generated (differential equation, first integral) pairs and uses guided reinforcement learning to outperform larger models and Mathematica on first-integral benchmarks at lower cost.
-
The finite expression method for turbulent dynamics with high-order moment recovery
A two-stage symbolic regression plus generative model framework recovers governing interaction terms and forcing in stochastic triad models while accurately predicting statistical moments up to order five.
-
Neural Enhancement of Analytical Appearance Models
Neural enhancement replaces selected computational nodes in analytical BRDF models with MLPs identified via hypercube search, yielding accurate, compact models that fit measured reflectance data better than pure analy...
-
Neuro-Symbolic ODE Discovery with Latent Grammar Flow
Latent Grammar Flow discovers ODEs by placing grammar-based equation representations in a discrete latent space, using a behavioral loss to cluster similar equations, and sampling via a discrete flow model guided by d...
-
Symbolic recovery of PDEs from measurement data
Symbolic rational-function networks recover an admissible PDE from noiseless complete measurements and select the regularization-minimizing parameterization within the architecture.
-
Transformer Semantic Genetic Programming for d-dimensional Symbolic Regression Problems
TSGP uses a pre-trained transformer as a semantic variation operator in genetic programming, generalizes across d-dimensional problems, and outperforms standard GP, SLIM_GSGP, Deep Symbolic Regression, and Denoising A...
-
Validating Causal Abstraction Metrics on Simulated Complex Systems
Authors create a benchmark across discrete/continuous and static/dynamical systems and introduce the Causal Abstraction Error (CAE) metric that reliably distinguishes valid from invalid causal abstractions when it inc...
-
EditSR: Enhancing Neural Symbolic Regression via Edit-based Rectification
EditSR improves neural symbolic regression accuracy on complex expressions by pretraining an edit-based rectifier on state-transition correction chains that enforce syntactic validity and condition edits only on the c...
-
STRIDE: A Self-Reflective Agent Framework for Reliable Automatic Equation Discovery
STRIDE is a self-reflective agent framework that improves accuracy, OOD robustness, and structural recovery in LLM-based symbolic regression by integrating generation, evaluation, repair, and diversity-preserving memory.
-
GESR: A Genetic Programming-Based Symbolic Regression Method with Gene Editing
GESR uses BERT models as guided 'gene editors' within genetic programming to direct mutations and crossovers, yielding higher efficiency and competitive performance on symbolic regression benchmarks.
-
GESR: A Genetic Programming-Based Symbolic Regression Method with Gene Editing
GESR uses two BERT models to intelligently guide mutations and crossovers in genetic programming for symbolic regression, claiming better efficiency than standard GP.
-
GESR: A Genetic Programming-Based Symbolic Regression Method with Gene Editing
GESR uses two BERT models to intelligently direct mutations and crossovers inside genetic programming, yielding higher efficiency and competitive accuracy on symbolic regression benchmarks.
-
Demystifying Deep Reinforcement Learning: A Neuro-Symbolic Framework for Interpretable Open RAN Automation
DeRAN converts opaque DRL policies for O-RAN tasks into interpretable symbolic policies via concept abstraction, deep symbolic regression, and neurally guided logic, retaining 78-87% of DRL performance on a live 5G testbed.
-
Demystifying Deep Reinforcement Learning: A Neuro-Symbolic Framework for Interpretable Open RAN Automation
DeRAN converts black-box DRL policies into interpretable symbolic representations for O-RAN automation, retaining 78-87% of original performance while adding built-in transparency.
-
Intentmaking and Sensemaking: Human Interaction with AI-Guided Mathematical Discovery
Expert mathematicians using an AI coding agent for discovery engage in repeated cycles of intentmaking to define goals and sensemaking to interpret outputs.
-
Programmatic Context Augmentation for LLM-based Symbolic Regression
Programmatic context augmentation lets LLM-based symbolic regression perform code-driven data analysis during search, yielding superior efficiency and accuracy over baselines on LLM-SRBench.
-
Neuro-Symbolic AI for Analytical Solutions of Differential Equations
SIGS is a neuro-symbolic framework that discovers analytical solutions to PDEs by generating grammar-constrained expressions, embedding them in a topology-regularised latent manifold, and refining structure and coeffi...
-
Discovering interpretable low-dimensional dynamics using maximum entropy
Edwin integrates dynamic maximum entropy dimensionality reduction with symbolic regression to recover physically interpretable low-dimensional dynamics from high-dimensional observations that generalize to unseen conditions.
-
ChatSR: Multimodal Large Language Models for Scientific Formula Discovery
ChatSR aligns scientific data encoders with LLMs to produce formulas that fit data and satisfy explicit priors, reporting SOTA results on 13 symbolic regression benchmarks plus zero-shot handling of unseen prior types.
-
PandaAI: A Practical Agent CQ2 for Neuro-symbolic Data Analysis And Integrated Decision-Making in Quantitative Finance
PandaAI is a closed-loop neuro-symbolic LLM agent for quantitative finance that reports 18.2% higher Rank IC and 25.7% lower max drawdown than SOTA time-series models on CSI 300 data.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.