knowledge-base-1

Symbolic Regression

3260 papers • 126 benchmarks • 313 datasets

producing a mathematical expression (symbolic expression) that fits a given tabular data.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in symbolic-regression-1

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find symbolic-regression-1 models and implementations

wassimtenachi/physo

4 papers 1,737

Datasets

SRSD-Feynman (Easy set)

SRSD-Feynman (Hard set)

SRSD-Feynman (Medium set)

SESYD Dataset

Subtasks

No subtasks available.

Most implemented papers

(Exhaustive) Symbolic Regression and model selection by minimum description length

Harry Desmond•Wed Jul 16 2025

This work proposes an exhaustive search and model selection by the minimum description length principle, which allows accuracy and complexity to be directly traded off by measuring each in units of information.

1

Content

brendenpetersen/deep-symbolic-optim…

3 papers 496

deep-symbolic-mathematics/TPSR

3 papers 32

0

Paper Graph

Contemporary Symbolic Regression Methods and their Relative Performance

W. L. Cava, P. Orzechowski, J. Moore, M. Virgolin, Bogdan Burlacu, Fabr'icio Olivetti de Francca, Ying Jin, M. Kommenda•Wed Jul 28 2021

It is concluded that the best performing methods for real-world regression combine genetic algorithms with parameter estimation and/or semantic search drivers, and the best performing methods for real-world regression combine genetic algorithms with parameter estimation and/or semantic search drivers.

343 0

Paper Graph

OccamNet: A Fast Neural Model for Symbolic Regression at Scale

Pawan Goyal, Samuel Kim, Allan Costa, Rumen Dangovski, Owen Dugan, Marin Soljavci'c, J. Jacobson•Wed Jul 15 2020

OccamNet is introduced, a neural network model that finds interpretable, compact, and sparse symbolic fits to data, a la Occam's razor, and defines a probability distribution over functions with efficient sampling and function evaluation.

14 0

Paper Graph

Grammar Variational Autoencoder

Matt J. Kusner, José Miguel Hernández-Lobato, Brooks Paige•Sun Mar 05 2017

Surprisingly, it is shown that not only does the model more often generate valid outputs, it also learns a more coherent latent space in which nearby points decode to similar discrete outputs.

917 0

Paper Graph

Learning a Formula of Interpretability to Learn Interpretable Formulas

M. Virgolin, A. D. Lorenzo, Eric Medvet, Francesca Randone•Wed Apr 22 2020

An ML model of non-trivial Proxies of Human Interpretability can be learned from human feedback, then this model can be incorporated within an ML training process to directly optimize for interpretability, and the results show that the use of this model leads to formulas that are significantly more or equally accurate.

40 0

Paper Graph

End-to-end symbolic regression with transformers

Guillaume Lample, Pierre-Alexandre Kamienny, Stéphane d'Ascoli, Franccois Charton•Thu Apr 21 2022

This paper tasks a Transformer to directly predict the full mathematical expression, constants included, and presents ablations to show that this end-to-end approach yields better results, sometimes even without the refinement step.

238 0

Paper Graph

Discovering Symbolic Models from Deep Learning with Inductive Biases

Miles Cranmer, P. Battaglia, D. Spergel, S. Ho, Alvaro Sanchez-Gonzalez, Rui Xu, K. Cranmer•Thu Jun 18 2020

The correct known equations, including force laws and Hamiltonians, can be extracted from the neural network and a new analytic formula is discovered which can predict the concentration of dark matter from the mass distribution of nearby cosmic structures.

585 0

Paper Graph

On Neural Differential Equations

Patrick Kidger•Thu Feb 03 2022

This doctoral thesis provides an in-depth survey of neural differential equations, a conjoining of dynamical systems and deep learning, and hopes it will provide a useful reference for the current state of the art.

423 0

Paper Graph

Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl

Miles Cranmer•Mon May 01 2023

A new benchmark, "EmpiricalBench," is introduced to quantify the applicability of symbolic regression algorithms in science, and measures recovery of historical empirical equations from original and synthetic datasets.

69 0

Paper Graph

AI Feynman: A physics-inspired method for symbolic regression

S. Udrescu, Max Tegmark•Sun May 26 2019

This work develops a recursive multidimensional symbolic regression algorithm that combines neural network fitting with a suite of physics-inspired techniques and improves the state-of-the-art success rate.

1094 0

Paper Graph

Adding a benchmark result helps the community track progress.