mlsanityData to 7 Oct 2026

AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity

arXiv 2006.10782 ↗First posted 18 Jun 2020cs.LG cs.AI cs.ITcited by 140

Not on the map. Why?

Abstract (arXiv)

We present an improved method for symbolic regression that seeks to fit data to formulas that are Pareto-optimal, in the sense of having the best accuracy for a given complexity. It improves on the previous state-of-the-art by typically being orders of magnitude more robust toward noise and bad data, and also by discovering many formulas that stumped previous methods. We develop a method for discovering generalized symmetries (arbitrary modularity in the computational graph of a formula) from gradient properties of a neural network fit. We use normalizing flows to generalize our symbolic regression method to probability distributions from which we only have samples, and employ statistical hypothesis testing to accelerate robust brute-force search.

Key facts. Cited by 140 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 20; 2023: 31; 2024: 26; 2025: 35; 2026: 13.

140 papers.

Sort:

By area:

  1. 2024KAN: Kolmogorov-Arnold Networkscited by 634
  2. 2021Neural Symbolic Regression that Scalescited by 185
  3. 2024LLM-SR: Scientific Equation Discovery via Programming with Large Language Modelscited by 117
  4. 2024KAN 2.0: Kolmogorov-Arnold Networks Meet Sciencecited by 116
  5. 2024LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discoverycited by 82
  6. 2023A Mathematical Guide to Operator Learningcited by 74
  7. 2023Transformer-based Planning for Symbolic Regressioncited by 72
  8. 2022Symbolic Physics Learner: Discovering governing equations via Monte Carlo tree searchcited by 61
  9. 2022Rethinking Symbolic Regression Datasets and Benchmarks for Scientific Discoverycited by 44
  10. 2024Towards Scientific Discovery with Generative AI: Progress, Opportunities, and Challengescited by 41
  11. 2023Seeing is Believing: Brain-Inspired Modular Training for Mechanistic Interpretabilitycited by 38
  12. 2023Interpretable Machine Learning for Science with PySR and SymbolicRegression.jlcited by 36
38 more
  1. 2023Discovering Causal Relations and Equations from Datacited by 33
  2. 2025NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agentscited by 32
  3. 2021Machine-learning hidden symmetriescited by 31
  4. 2022A computational framework for physics-informed symbolic regression with straightforward integration of domain knowledgecited by 31
  5. 2022Exhaustive Symbolic Regressioncited by 29
  6. 2023Predicting Ordinary Differential Equations with Transformerscited by 26
  7. 2022Learning Green's functions associated with time-dependent partial differential equationscited by 25
  8. 2023Generative learning for nonlinear dynamicscited by 22
  9. 2022AI Poincar'e 2.0: Machine Learning Conservation Laws from Differential Equationscited by 20
  10. 2023Benchmarking sparse system identification with low-dimensional chaoscited by 19
  11. 2023Controllable Neural Symbolic Regressioncited by 19
  12. 2024Opening the AI black box: program synthesis via mechanistic interpretabilitycited by 19
  13. 2022Taylor Genetic Programming for Symbolic Regressioncited by 18
  14. 2023Automated Scientific Discovery: From Equation Discovery to Autonomous Discovery Systemscited by 18
  15. 2023Evolving Scientific Discovery by Unifying Data and Background Knowledge with AI Hilbertcited by 18
  16. 2024Symbolic regression via MDLformer-guided search: from minimizing prediction error to minimizing description lengthcited by 16
  17. 2022Precision Machine Learningcited by 14
  18. 2023A Neural-Guided Dynamic Symbolic Network for Exploring Mathematical Expressions from Datacited by 14
  19. 2024MMSR: Symbolic Regression is a Multi-Modal Information Fusion Taskcited by 13
  20. 2025AgenticSciML: Collaborative Multi-Agent Systems for Emergent Discovery in Scientific Machine Learningcited by 13
  21. 2026Think like a Scientist: Physics-guided LLM Agent for Equation Discoverycited by 13
  22. 2021From Kepler to Newton: Explainable AI for Sciencecited by 12
  23. 2021Physics-Augmented Learning: A New Paradigm Beyond Physics-Informed Learningcited by 11
  24. 2022GSR: A Generalized Symbolic Regression Approachcited by 11
  25. 2023Physics-aware Machine Learning Revolutionizes Scientific Paradigm for Machine Learning and Process-based Hydrologycited by 11
  26. 2025Interpretable Machine Learning in Physics: A Reviewcited by 11
  27. 2021Quantifying Local Specialization in Deep Neural Networkscited by 10
  28. 2022Automatic and effective discovery of quantum kernelscited by 10
  29. 2023Priors for symbolic regressioncited by 10
  30. 2024Discovering Mathematical Formulas from Data via GPT-guided Monte Carlo Tree Searchcited by 10
  31. 2025A Neural Symbolic Model for Space Physicscited by 10
  32. 2025Quantum Variational Activation Functions Empower Kolmogorov-Arnold Networkscited by 10
  33. 2021Inferring the Structure of Ordinary Differential Equationscited by 7
  34. 2021AI Descartes: Combining Data and Theory for Derivable Scientific Discoverycited by 7
  35. 2022D-CIPHER: Discovery of Closed-form Partial Differential Equationscited by 7
  36. 2023RSRM: Reinforcement Symbolic Regression Machinecited by 7
  37. 2024Creativity in AI: Progresses and Challengescited by 7
  38. 2025Exploiting Edited Large Language Models as General Scientific Optimizerscited by 7

50 most cited of 140 All 140 (JSON)