---
title: "Interpretable Machine Learning for Science with PySR and"
description: "To address this, the paper presents PySR, a Python package running on the Julia engine… 103 references, cited by 26 papers here."
authors: ["Miles Cranmer (Princeton University", "Flatiron Institute)"]
year: 2023
venue: "arXiv:2305.01582"
source: "https://arxiv.org/abs/2305.01582"
doi: "10.48550/arxiv.2305.01582"
arxiv: "2305.01582"
licence: "arXiv non-exclusive distribution license"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/university-2023-interpretable-machine-learning-science/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/university-2023-interpretable-machine-learning-science/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2023](https://md.research.elamur.ai/free/en/papers/2023/page/4/) / Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl

# Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl

**Authors:** Miles Cranmer (Princeton University and Flatiron Institute) · **Year:** 2023 · **Venue:** arXiv:2305.01582 · **Licence:** [arXiv non-exclusive distribution license](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2305.01582) · [PDF](https://arxiv.org/pdf/2305.01582) · [DOI 10.48550/arxiv.2305.01582](https://doi.org/10.48550/arxiv.2305.01582) · [arXiv 2305.01582](https://arxiv.org/abs/2305.01582) · [OpenAlex](https://openalex.org/W4368303491)

**Citations:** 190 citations (OpenAlex, 2026-10-14) · [26](https://md.research.elamur.ai/free/en/papers/university-2023-interpretable-machine-learning-science/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Symbolic regression (SR) searches over analytic expressions to find formulas that are both accurate and readable. It automates the kind of empirical law-finding that produced Kepler's third law or Planck's law. The author argues that most existing SR tools are tuned to synthetic benchmarks and fall short of what scientists need. Those needs include fitting unknown real constants, handling noisy and heteroscedastic data, piecewise forms, custom operators, constraints, high-dimensional or non-tabular inputs, and open, easy-to-use software.

To address this, the paper presents PySR, a Python package running on the Julia engine SymbolicRegression.jl. Its search is a multi-population evolutionary algorithm built around a cycle of evolving, simplifying and constant-optimizing candidate expressions. It also uses age-regularized replacement and simulated annealing. The backend compiles user-defined operators into fast SIMD code, supports automatic differentiation, and scales across cluster cores.

The paper also introduces EmpiricalBench, a benchmark that tests whether algorithms can rediscover historical empirical equations. On it, classic untrained methods outperformed pure deep-learning approaches. This suggests careful search heuristics still matter for real scientific data.

## Key points
- PySR is distributed via PyPI and Conda under `pysr`. Its backend, SymbolicRegression.jl, is in the Julia registry and can be used directly from Julia. It was first released publicly in 2020.
- The algorithm modifies classic tournament-selection evolution in several ways:
  - it removes the oldest individual rather than the weakest (age-regularized evolution);
  - it adds simulated annealing, with rejection probability controlled by temperature T and hyperparameter α;
  - it runs asynchronous migration between populations.
- EmpiricalBench measures recovery of known empirical laws from original and synthetic datasets. On it, PySR, Operon, DSR and QLattice all beat the deep-learning methods EQL and SR-Transformer. SR-Transformer is pre-trained on billions of synthetic expressions, yet still came out behind.
- PySR has been used to model cloud cover, electron transfer in materials, astrophysical relations, international trade rules, and gravitational-wave source populations.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Princeton University](https://md.research.elamur.ai/free/en/universities/princeton-university/) — University, Princeton, United States · 137 works · 53,849 citations
- [Flatiron Institute](https://md.research.elamur.ai/free/en/labs/flatiron-institute/) — Research institute, New York, United States · 2 works · 235 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 19,503 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 18,805 works · [⚛️ Physics and Astronomy](https://md.research.elamur.ai/free/en/shelves/physics-and-astronomy/) · 70 works · [⚛️ Statistical and Nonlinear Physics](https://md.research.elamur.ai/free/en/shelves/physics-and-astronomy/statistical-and-nonlinear-physics/) · 60 works · [⚛️ Nuclear and High Energy Physics](https://md.research.elamur.ai/free/en/shelves/physics-and-astronomy/nuclear-and-high-energy-physics/) · 2 works

## Cite

Cite as: Miles Cranmer (Princeton University and Flatiron Institute). 2023. Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl. arXiv:2305.01582.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{university2023interpretable,
  title = {{Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl}},
  author = {Miles Cranmer (Princeton University and Flatiron Institute)},
  year = {2023},
  doi = {10.48550/arxiv.2305.01582},
  eprint = {2305.01582},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2305.01582}
}
```

- [← previous Safe RLHF: Safe Reinforcement Learning from Human Feedback](https://md.research.elamur.ai/free/en/papers/dai-2023-safe-rlhf-safe-reinforcement-learning/)
- [next → LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://md.research.elamur.ai/free/en/papers/liu-2023-llm-p-empowering-large-language/)
- [↑ back to papers of 2023](https://md.research.elamur.ai/free/en/papers/2023/page/4/)

## References

103 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Stephen Hawking. On the Shoulders of Giants: The Great Works of Physics and Astronomy. Running, Philadelphia, Pa.; London, 2004. [find](https://scholar.google.com/scholar?q=Stephen+Hawking%2E+On+the+Shoulders+of+Giants%3A+The+Great+Works+of+Physics+and+Astronomy%2E+Running%2C+Philadelphia%2C+Pa%2E%3B+London%2C+2004%2E)
2. Max Planck. Über eine Verbesserung der Wien’schen Spectralgleichung. Friedr. Vieweg & Sohn, 1900. [find](https://scholar.google.com/scholar?q=Max+Planck%2E+%C3%9Cber+eine+Verbesserung+der+Wien%E2%80%99schen+Spectralgleichung%2E+Friedr%2E+Vieweg+%26+Sohn%2C+1900%2E)
3. Marco Virgolin and Solon P. Pissis. [Symbolic Regression is NP-hard](https://md.research.elamur.ai/free/en/papers/virgolin-2022-symbolic-regression-np-hard/), July 2022.
4. Donald Gerwin. Information processing, data inferences, and scientific generalization. Behavioral Science, 19(5):314–325, 1974. [find](https://scholar.google.com/scholar?q=Donald+Gerwin%2E+Information+processing%2C+data+inferences%2C+and+scientific+generalization%2E+Behavioral+Science%2C+19%285%29%3A314%E2%80%93325%2C+1974%2E)
5. Pat Langley. [BACON: A production system that discovers empirical laws](https://md.research.elamur.ai/free/en/papers/langley-1977-bacon-production-system-discovers-empirical/). In IJCAI, 1977.
6. Pat Langley. Rediscovering physics with BA-CON.3. In Proceedings of the 6th International Joint Conference on Artificial Intelligence - Volume 1, IJCAI’79, pages 505–507, San Francisco, CA, USA, 1979. Morgan Kaufmann Publishers Inc. [find](https://scholar.google.com/scholar?q=Pat+Langley%2E+Rediscovering+physics+with+BA%2DCON%2E3%2E+In+Proceedings+of+the+6th+International+Joint+Conference+on+Artificial+Intelligence+%2D+Volume+1%2C+IJCAI%E2%80%9979%2C+pages+505%E2%80%93507%2C+San+Francisco%2C+CA%2C+USA%2C+1979%2E)
7. Pat Langley, Gary L. Bradshaw, and Herbert A. Simon. BACON.5: The discovery of conservation laws. In IJCAI, 1981. [find](https://scholar.google.com/scholar?q=Pat+Langley%2C+Gary+L%2E+Bradshaw%2C+and+Herbert+A%2E+Simon%2E+BACON%2E5%3A+The+discovery+of+conservation+laws%2E+In+IJCAI%2C+1981%2E)
8. Pat Langley and Jan M. Zytkow. Data-driven approaches to empirical discovery. Artificial Intelligence, 40(1):283–312, 1989. [find](https://scholar.google.com/scholar?q=Pat+Langley+and+Jan+M%2E+Zytkow%2E+Data%2Ddriven+approaches+to+empirical+discovery%2E+Artificial+Intelligence%2C+40%281%29%3A283%E2%80%93312%2C+1989%2E)
9. John R. Koza. Genetic programming as a means for programming computers by natural selection. Statistics and Computing, 4(2):87– 112, June 1994. [find](https://scholar.google.com/scholar?q=John+R%2E+Koza%2E+Genetic+programming+as+a+means+for+programming+computers+by+natural+selection%2E+Statistics+and+Computing%2C+4%282%29%3A87%E2%80%93+112%2C+June+1994%2E)
10. Josh Bongard and Hod Lipson. From the Cover: Automated reverse engineering of nonlinear dynamical systems. Proceedings of the National Academy of Science, 104(24):9943–9948, June 2007. [find](https://scholar.google.com/scholar?q=Josh+Bongard+and+Hod+Lipson%2E+From+the+Cover%3A+Automated+reverse+engineering+of+nonlinear+dynamical+systems%2E+Proceedings+of+the+National+Academy+of+Science%2C+104%2824%29%3A9943%E2%80%939948%2C+June+2007%2E)
11. Michael Schmidt and Hod Lipson. Distilling Free-Form Natural Laws from Experimental Data. Science, 324(5923):81–85, April 2009. [find](https://scholar.google.com/scholar?q=Michael+Schmidt+and+Hod+Lipson%2E+Distilling+Free%2DForm+Natural+Laws+from+Experimental+Data%2E+Science%2C+324%285923%29%3A81%E2%80%9385%2C+April+2009%2E)
12. M. Schmidt and H. Lipson. Symbolic regression of implicit equations. Genetic Programming Theory and Practice VII, pages 73–85, 2010. [find](https://scholar.google.com/scholar?q=M%2E+Schmidt+and+H%2E+Lipson%2E+Symbolic+regression+of+implicit+equations%2E+Genetic+Programming+Theory+and+Practice+VII%2C+pages+73%E2%80%9385%2C+2010%2E)
13. S. Wagner and M. Affenzeller. HeuristicLab: A Generic and Extensible Optimization Environment. In Bernardete Ribeiro, Rudolf F. Albrecht, Andrej Dobnikar, David W. Pearson, and Nigel C. Steele, editors, Adaptive and Natural Computing Algorithms, pages 538–541, Vienna, 2005. Springer. [find](https://scholar.google.com/scholar?q=S%2E+Wagner+and+M%2E+Affenzeller%2E+HeuristicLab%3A+A+Generic+and+Extensible+Optimization+Environment%2E+In+Bernardete+Ribeiro%2C+Rudolf+F%2E+Albrecht%2C+Andrej+Dobnikar%2C+David+W%2E+Pearson%2C+and+Nigel+C%2E+Steele%2C+editor)
14. Kalyanmoy Deb, Samir Agrawal, Amrit Pratap, and T. Meyarivan. A Fast Elitist Non-dominated Sorting Genetic Algorithm for Multi-objective Optimization: NSGA-II. In Marc Schoenauer, Kalyanmoy Deb, Günther Rudolph, Xin Yao, Evelyne Lutton, Juan Julian Merelo, and Hans-Paul Schwefel, editors, Parallel P… [find](https://scholar.google.com/scholar?q=Kalyanmoy+Deb%2C+Samir+Agrawal%2C+Amrit+Pratap%2C+and+T%2E+Meyarivan%2E+A+Fast+Elitist+Non%2Ddominated+Sorting+Genetic+Algorithm+for+Multi%2Dobjective+Optimization%3A+NSGA%2DII%2E+In+Marc+Schoenauer%2C+Kalyanmoy+Deb%2C+G%C3%BCnth)
15. K. Deb, A. Pratap, S. Agarwal, and T. Meyarivan. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation, 6(2):182–197, April 2002. [find](https://scholar.google.com/scholar?q=K%2E+Deb%2C+A%2E+Pratap%2C+S%2E+Agarwal%2C+and+T%2E+Meyarivan%2E+A+fast+and+elitist+multiobjective+genetic+algorithm%3A+NSGA%2DII%2E+IEEE+Transactions+on+Evolutionary+Computation%2C+6%282%29%3A182%E2%80%93197%2C+April+2002%2E)
16. J.W. Davidson, D.A. Savic, and G.A. Walters. Symbolic and numerical regression: Experiments and applications. Information Sciences, 150(1):95–117, 2003. [find](https://scholar.google.com/scholar?q=J%2EW%2E+Davidson%2C+D%2EA%2E+Savic%2C+and+G%2EA%2E+Walters%2E+Symbolic+and+numerical+regression%3A+Experiments+and+applications%2E+Information+Sciences%2C+150%281%29%3A95%E2%80%93117%2C+2003%2E)
17. Kyle Cranmer and R. Sean Bowman. Physic-sGP: A Genetic Programming approach to event selection. Computer Physics Communications, 167(3):165–176, May 2005. [find](https://scholar.google.com/scholar?q=Kyle+Cranmer+and+R%2E+Sean+Bowman%2E+Physic%2DsGP%3A+A+Genetic+Programming+approach+to+event+selection%2E+Computer+Physics+Communications%2C+167%283%29%3A165%E2%80%93176%2C+May+2005%2E)
18. William La Cava, Lee Spector, and Kourosh Danai. Epsilon-Lexicase Selection for Regression. In Proceedings of the Genetic and Evolutionary Computation Conference 2016, GECCO ’16, pages 741–748, New York, NY, USA, July 2016. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=William+La+Cava%2C+Lee+Spector%2C+and+Kourosh+Danai%2E+Epsilon%2DLexicase+Selection+for+Regression%2E+In+Proceedings+of+the+Genetic+and+Evolutionary+Computation+Conference+2016%2C+GECCO+%E2%80%9916%2C+pages+741%E2%80%93748%2C+New+Yo)
19. William La Cava, Thomas Helmuth, Lee Spector, and Jason H. Moore. A probabilistic and multi-objective analysis of lexicase selection and epsilon-lexicase selection, April 2018. [find](https://scholar.google.com/scholar?q=William+La+Cava%2C+Thomas+Helmuth%2C+Lee+Spector%2C+and+Jason+H%2E+Moore%2E+A+probabilistic+and+multi%2Dobjective+analysis+of+lexicase+selection+and+epsilon%2Dlexicase+selection%2C+April+2018%2E)
20. Marco Virgolin, Tanja Alderliesten, Cees Witteveen, and Peter A. N. Bosman. Scalable genetic programming by gene-pool optimal mixing and input-space entropy-based building-block learning. In Proceedings of the Genetic and Evolutionary Computation Conference, GECCO ’17, pages 1041–1048, New York, NY,… [find](https://scholar.google.com/scholar?q=Marco+Virgolin%2C+Tanja+Alderliesten%2C+Cees+Witteveen%2C+and+Peter+A%2E+N%2E+Bosman%2E+Scalable+genetic+programming+by+gene%2Dpool+optimal+mixing+and+input%2Dspace+entropy%2Dbased+building%2Dblock+learning%2E+In+Proceedin)
21. Marco Virgolin, Tanja Alderliesten, Cees Witteveen, and Peter A. N. Bosman. Improving Model-based Genetic Programming for Symbolic Regression of Small Expressions. Evolutionary Computation, 29(2):211–237, June 2021. [find](https://scholar.google.com/scholar?q=Marco+Virgolin%2C+Tanja+Alderliesten%2C+Cees+Witteveen%2C+and+Peter+A%2E+N%2E+Bosman%2E+Improving+Model%2Dbased+Genetic+Programming+for+Symbolic+Regression+of+Small+Expressions%2E+Evolutionary+Computation%2C+29%282%29%3A211%E2%80%93)
22. Miles D. Cranmer, Rui Xu, Peter Battaglia, and Shirley Ho. Learning Symbolic Physics with Graph Networks. ML4Physics Workshop @ NeurIPS 2019, November 2019. [find](https://scholar.google.com/scholar?q=Miles+D%2E+Cranmer%2C+Rui+Xu%2C+Peter+Battaglia%2C+and+Shirley+Ho%2E+Learning+Symbolic+Physics+with+Graph+Networks%2E+ML4Physics+Workshop+%40+NeurIPS+2019%2C+November+2019%2E)
23. Miles Cranmer, Alvaro Sanchez-Gonzalez, Peter Battaglia, Rui Xu, Kyle Cranmer, David Spergel, and Shirley Ho. [Discovering Symbolic Models from Deep Learning with Inductive Biases](https://md.research.elamur.ai/free/en/papers/cranmer-2020-discovering-symbolic-models-deep/). NeurIPS, June 2020.
24. Miles Cranmer, Can Cui, Drummond B Fielding, Shirley Ho, Alvaro Sanchez-Gonzalez, Kimberly Stachenfeld, Tobias Pfaff, et al. Disentangled Sparsity Networks for Explainable AI. Workshop on Sparse Neural Networks, page 7, July 2021. [find](https://scholar.google.com/scholar?q=Miles+Cranmer%2C+Can+Cui%2C+Drummond+B+Fielding%2C+Shirley+Ho%2C+Alvaro+Sanchez%2DGonzalez%2C+Kimberly+Stachenfeld%2C+Tobias+Pfaff%2C+et+al%2E+Disentangled+Sparsity+Networks+for+Explainable+AI%2E+Workshop+on+Sparse+Neura)
25. Ying Jin, Weilin Fu, Jian Kang, Jiadong Guo, and Jian Guo. Bayesian Symbolic Regression. January 2020. [find](https://scholar.google.com/scholar?q=Ying+Jin%2C+Weilin+Fu%2C+Jian+Kang%2C+Jiadong+Guo%2C+and+Jian+Guo%2E+Bayesian+Symbolic+Regression%2E+January+2020%2E)
26. Roger Guimerà, Ignasi Reichardt, Antoni Aguilar-Mogas, Francesco A. Massucci, Manuel Miranda, Jordi Pallarès, and Marta Sales-Pardo. A Bayesian machine scientist to aid in the solution of challenging scientific problems. Science Advances, 6(5), 2020. [find](https://scholar.google.com/scholar?q=Roger+Guimer%C3%A0%2C+Ignasi+Reichardt%2C+Antoni+Aguilar%2DMogas%2C+Francesco+A%2E+Massucci%2C+Manuel+Miranda%2C+Jordi+Pallar%C3%A8s%2C+and+Marta+Sales%2DPardo%2E+A+Bayesian+machine+scientist+to+aid+in+the+solution+of+challenging+)
27. Brenden K. Petersen, Mikel Landajuela, T. Nathan Mundhenk, Claudio P. Santiago, Soo K. Kim, and Joanne T. Kim. Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients, April 2021. [find](https://scholar.google.com/scholar?q=Brenden+K%2E+Petersen%2C+Mikel+Landajuela%2C+T%2E+Nathan+Mundhenk%2C+Claudio+P%2E+Santiago%2C+Soo+K%2E+Kim%2C+and+Joanne+T%2E+Kim%2E+Deep+symbolic+regression%3A+Recovering+mathematical+expressions+from+data+via+risk%2Dseeking+)
28. Li Li, Minjie Fan, Rishabh Singh, and Patrick Riley. Neural-guided symbolic regression with asymptotic constraints. arXiv preprint arXiv:1901.07714, 2019. — [arXiv:1901.07714](https://arxiv.org/abs/1901.07714) [find](https://scholar.google.com/scholar?q=Li+Li%2C+Minjie+Fan%2C+Rishabh+Singh%2C+and+Patrick+Riley%2E+Neural%2Dguided+symbolic+regression+with+asymptotic+constraints%2E+arXiv+preprint+arXiv%3A1901%2E07714%2C+2019%2E+%E2%80%94+%5BarXiv%3A1901%2E07714%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F19)
29. Stéphane d’Ascoli, Pierre-Alexandre Kamienny, Guillaume Lample, and François Charton. [Deep Symbolic Regression for Recurrent Sequences](https://md.research.elamur.ai/free/en/papers/ascoli-2022-deep-symbolic-regression-recurrent-sequences/), June 2022.
30. Pierre-Alexandre Kamienny, Stéphane d’Ascoli, Guillaume Lample, and François Charton. [End-to-end symbolic regression with transformers](https://md.research.elamur.ai/free/en/papers/kamienny-2022-end-end-symbolic-regression-transformers/). April 2022.
31. Silviu-Marian Udrescu, Andrew Tan, Jiahai Feng, Orisvaldo Neto, Tailin Wu, and Max Tegmark. AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity. In Advances in Neural Information Processing Systems, volume 33, pages 4860–4871. Curran Associates, Inc., 2020. [find](https://scholar.google.com/scholar?q=Silviu%2DMarian+Udrescu%2C+Andrew+Tan%2C+Jiahai+Feng%2C+Orisvaldo+Neto%2C+Tailin+Wu%2C+and+Max+Tegmark%2E+AI+Feynman+2%2E0%3A+Pareto%2Doptimal+symbolic+regression+exploiting+graph+modularity%2E+In+Advances+in+Neural+Inform)
32. Ziming Liu and Max Tegmark. [AI poincaré: Machine learning conservation laws from trajectories](https://md.research.elamur.ai/free/en/papers/liu-2020-ai-poincare-machine-learning/). arXiv e-prints, page arXiv:2011.04698, November 2020.
33. Sebastian J. Wetzel, Roger G. Melko, Joseph Scott, Maysum Panju, and Vijay Ganesh. Discovering symmetry invariants and conserved quantities by interpreting siamese neural networks. Physical Review Research, 2(3):033499, September 2020. [find](https://scholar.google.com/scholar?q=Sebastian+J%2E+Wetzel%2C+Roger+G%2E+Melko%2C+Joseph+Scott%2C+Maysum+Panju%2C+and+Vijay+Ganesh%2E+Discovering+symmetry+invariants+and+conserved+quantities+by+interpreting+siamese+neural+networks%2E+Physical+Review+Res)
34. Subham Sahoo, Christoph Lampert, and Georg Martius. Learning Equations for Extrapolation and Control. volume 80 of Proceedings of Machine Learning Research, pages 4442– 4450, Stockholmsmässan, Stockholm Sweden, July 2018. PMLR. [find](https://scholar.google.com/scholar?q=Subham+Sahoo%2C+Christoph+Lampert%2C+and+Georg+Martius%2E+Learning+Equations+for+Extrapolation+and+Control%2E+volume+80+of+Proceedings+of+Machine+Learning+Research%2C+pages+4442%E2%80%93+4450%2C+Stockholmsm%C3%A4ssan%2C+Stockho)
35. Steven Atkinson, Waad Subber, Liping Wang, Genghis Khan, Philippe Hawi, and Roger Ghanem. Data-driven discovery of free-form governing differential equations. arXiv preprint arXiv:1910.05117, 2019. — [arXiv:1910.05117](https://arxiv.org/abs/1910.05117) [find](https://scholar.google.com/scholar?q=Steven+Atkinson%2C+Waad+Subber%2C+Liping+Wang%2C+Genghis+Khan%2C+Philippe+Hawi%2C+and+Roger+Ghanem%2E+Data%2Ddriven+discovery+of+free%2Dform+governing+differential+equations%2E+arXiv+preprint+arXiv%3A1910%2E05117%2C+2019%2E+%E2%80%94+)
36. Andrew Slavin Ross, Ziwei Li, Pavel Perezhogin, Carlos Fernandez-Granda, and Laure Zanna. Benchmarking of machine learning ocean subgrid parameterizations in an idealized model, October 2022. [find](https://scholar.google.com/scholar?q=Andrew+Slavin+Ross%2C+Ziwei+Li%2C+Pavel+Perezhogin%2C+Carlos+Fernandez%2DGranda%2C+and+Laure+Zanna%2E+Benchmarking+of+machine+learning+ocean+subgrid+parameterizations+in+an+idealized+model%2C+October+2022%2E)
37. M. Brameier and W. Banzhaf. A comparison of linear genetic programming and neural networks in medical data mining. IEEE Transactions on Evolutionary Computation, 5(1):17– 26, February 2001. [find](https://scholar.google.com/scholar?q=M%2E+Brameier+and+W%2E+Banzhaf%2E+A+comparison+of+linear+genetic+programming+and+neural+networks+in+medical+data+mining%2E+IEEE+Transactions+on+Evolutionary+Computation%2C+5%281%29%3A17%E2%80%93+26%2C+February+2001%2E)
38. Aytac Guven. Linear genetic programming for time-series modelling of daily flow rate. Journal of Earth System Science, 118(2):137–146, April 2009. [find](https://scholar.google.com/scholar?q=Aytac+Guven%2E+Linear+genetic+programming+for+time%2Dseries+modelling+of+daily+flow+rate%2E+Journal+of+Earth+System+Science%2C+118%282%29%3A137%E2%80%93146%2C+April+2009%2E)
39. He Ma, Arunachalam Narayanaswamy, Patrick Riley, and Li Li. Evolving symbolic density functionals. Science Advances, 8(36):eabq0279, September 2022. [find](https://scholar.google.com/scholar?q=He+Ma%2C+Arunachalam+Narayanaswamy%2C+Patrick+Riley%2C+and+Li+Li%2E+Evolving+symbolic+density+functionals%2E+Science+Advances%2C+8%2836%29%3Aeabq0279%2C+September+2022%2E)
40. Douglas Mota Dias and Marco Aurélio C. Pacheco. Describing Quantum-Inspired Linear Genetic Programming from symbolic regression problems. In 2012 IEEE Congress on Evolutionary Computation, pages 1–8, June 2012. [find](https://scholar.google.com/scholar?q=Douglas+Mota+Dias+and+Marco+Aur%C3%A9lio+C%2E+Pacheco%2E+Describing+Quantum%2DInspired+Linear+Genetic+Programming+from+symbolic+regression+problems%2E+In+2012+IEEE+Congress+on+Evolutionary+Computation%2C+pages+1%E2%80%938%2C+)
41. Steven L. Brunton, Joshua L. Proctor, and J. Nathan Kutz. Discovering governing equations from data by sparse identification of non-linear dynamical systems. Proceedings of the National Academy of Sciences, 113(15):3932– 3937, 2016. [find](https://scholar.google.com/scholar?q=Steven+L%2E+Brunton%2C+Joshua+L%2E+Proctor%2C+and+J%2E+Nathan+Kutz%2E+Discovering+governing+equations+from+data+by+sparse+identification+of+non%2Dlinear+dynamical+systems%2E+Proceedings+of+the+National+Academy+of+Sci)
42. Samuel H Rudy, Steven L Brunton, Joshua L Proctor, and J Nathan Kutz. Data-driven discovery of partial differential equations. Science Advances, 3(4):e1602614, 2017. [find](https://scholar.google.com/scholar?q=Samuel+H+Rudy%2C+Steven+L+Brunton%2C+Joshua+L+Proctor%2C+and+J+Nathan+Kutz%2E+Data%2Ddriven+discovery+of+partial+differential+equations%2E+Science+Advances%2C+3%284%29%3Ae1602614%2C+2017%2E)
43. Kathleen Champion, Bethany Lusch, J. Nathan Kutz, and Steven L. Brunton. Data-driven discovery of coordinates and governing equations. arXiv e-prints, page arXiv:1904.02107, March 2019. — [arXiv:1904.02107](https://arxiv.org/abs/1904.02107) [find](https://scholar.google.com/scholar?q=Kathleen+Champion%2C+Bethany+Lusch%2C+J%2E+Nathan+Kutz%2C+and+Steven+L%2E+Brunton%2E+Data%2Ddriven+discovery+of+coordinates+and+governing+equations%2E+arXiv+e%2Dprints%2C+page+arXiv%3A1904%2E02107%2C+March+2019%2E+%E2%80%94+%5BarXiv%3A1904%2E)
44. Bogdan Burlacu, Gabriel Kronberger, and Michael Kommenda. Operon C++: An efficient genetic programming framework for symbolic regression. In Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion, GECCO ’20, pages 1562– 1570, New York, NY, USA, July 2020. Association for C… [find](https://scholar.google.com/scholar?q=Bogdan+Burlacu%2C+Gabriel+Kronberger%2C+and+Michael+Kommenda%2E+Operon+C%2B%2B%3A+An+efficient+genetic+programming+framework+for+symbolic+regression%2E+In+Proceedings+of+the+2020+Genetic+and+Evolutionary+Computatio)
45. Trent McConaghy. FFX: Fast, Scalable, Deterministic Symbolic Regression Technology. In Rick Riolo, Ekaterina Vladislavleva, and Jason H. Moore, editors, Genetic Programming Theory and Practice IX, Genetic and Evolutionary Computation, pages 235–260. Springer, New York, NY, 2011. [find](https://scholar.google.com/scholar?q=Trent+McConaghy%2E+FFX%3A+Fast%2C+Scalable%2C+Deterministic+Symbolic+Regression+Technology%2E+In+Rick+Riolo%2C+Ekaterina+Vladislavleva%2C+and+Jason+H%2E+Moore%2C+editors%2C+Genetic+Programming+Theory+and+Practice+IX%2C+Gen)
46. Bethany Lusch, J. Nathan Kutz, and Steven L. Brunton. Deep learning for universal linear embeddings of nonlinear dynamics. Nature Communications, 9:4950, November 2018. [find](https://scholar.google.com/scholar?q=Bethany+Lusch%2C+J%2E+Nathan+Kutz%2C+and+Steven+L%2E+Brunton%2E+Deep+learning+for+universal+linear+embeddings+of+nonlinear+dynamics%2E+Nature+Communications%2C+9%3A4950%2C+November+2018%2E)
47. Gert-Jan Both, Subham Choudhury, Pierre Sens, and Remy Kusters. DeepMoD: Deep learning for Model Discovery in noisy data. 2019. [find](https://scholar.google.com/scholar?q=Gert%2DJan+Both%2C+Subham+Choudhury%2C+Pierre+Sens%2C+and+Remy+Kusters%2E+DeepMoD%3A+Deep+learning+for+Model+Discovery+in+noisy+data%2E+2019%2E)
48. Zhao Chen, Yang Liu, and Hao Sun. Deep learning of physical laws from scarce data. 2020. [find](https://scholar.google.com/scholar?q=Zhao+Chen%2C+Yang+Liu%2C+and+Hao+Sun%2E+Deep+learning+of+physical+laws+from+scarce+data%2E+2020%2E)
49. Christopher Rackauckas, Yingbo Ma, Julius Martensen, Collin Warner, Kirill Zubov, Rohit Supekar, Dominic Skinner, and Ali Ramadhan. Universal differential equations for scientific machine learning. arXiv preprint arXiv:2001.04385, 2020. [find](https://scholar.google.com/scholar?q=Christopher+Rackauckas%2C+Yingbo+Ma%2C+Julius+Martensen%2C+Collin+Warner%2C+Kirill+Zubov%2C+Rohit+Supekar%2C+Dominic+Skinner%2C+and+Ali+Ramadhan%2E+Universal+differential+equations+for+scientific+machine+learning%2E+ar)
50. Alison Cozad and Nikolaos V. Sahinidis. A global MINLP approach to symbolic regression. Mathematical Programming, 170(1):97– 119, July 2018. [find](https://scholar.google.com/scholar?q=Alison+Cozad+and+Nikolaos+V%2E+Sahinidis%2E+A+global+MINLP+approach+to+symbolic+regression%2E+Mathematical+Programming%2C+170%281%29%3A97%E2%80%93+119%2C+July+2018%2E)
51. Fabricio Olivetti de Franca. A Greedy Search Tree Heuristic for Symbolic Regression. Information Sciences, 442–443:18–32, May 2018. [find](https://scholar.google.com/scholar?q=Fabricio+Olivetti+de+Franca%2E+A+Greedy+Search+Tree+Heuristic+for+Symbolic+Regression%2E+Information+Sciences%2C+442%E2%80%93443%3A18%E2%80%9332%2C+May+2018%2E)
52. Cristina Cornelio, Sanjeeb Dash, Vernon Austel, Tyler Josephson, Joao Goncalves, Kenneth Clarkson, Nimrod Megiddo, et al. AI Descartes: Combining Data and Theory for Derivable Scientific Discovery. arXiv:2109.01634 [cs], October 2021. [find](https://scholar.google.com/scholar?q=Cristina+Cornelio%2C+Sanjeeb+Dash%2C+Vernon+Austel%2C+Tyler+Josephson%2C+Joao+Goncalves%2C+Kenneth+Clarkson%2C+Nimrod+Megiddo%2C+et+al%2E+AI+Descartes%3A+Combining+Data+and+Theory+for+Derivable+Scientific+Discovery%2E+ar)
53. A. M. Price-Whelan, B. M. Sip’ocz, H. M. G"unther, P. L. Lim, S. M. Crawford, S. Conseil, D. L. Shupe, et al. The Astropy Project: Building an Open-science Project and Status of the v2.0 Core Package. aj, 156:123, September 2018. [find](https://scholar.google.com/scholar?q=A%2E+M%2E+Price%2DWhelan%2C+B%2E+M%2E+Sip%E2%80%99ocz%2C+H%2E+M%2E+G%22unther%2C+P%2E+L%2E+Lim%2C+S%2E+M%2E+Crawford%2C+S%2E+Conseil%2C+D%2E+L%2E+Shupe%2C+et+al%2E+The+Astropy+Project%3A+Building+an+Open%2Dscience+Project+and+Status+of+the+v2%2E0+Core+Package%2E)
54. Astropy Collaboration, Adrian M. Price-Whelan, Pey Lian Lim, Nicholas Earl, Nathaniel Starkman, Larry Bradley, David L. Shupe, et al. The Astropy Project: Sustaining and Growing a Community-oriented Open-source Project and the Latest Major Release (v5.0) of the Core Package. The Astrophysical Journa… [find](https://scholar.google.com/scholar?q=Astropy+Collaboration%2C+Adrian+M%2E+Price%2DWhelan%2C+Pey+Lian+Lim%2C+Nicholas+Earl%2C+Nathaniel+Starkman%2C+Larry+Bradley%2C+David+L%2E+Shupe%2C+et+al%2E+The+Astropy+Project%3A+Sustaining+and+Growing+a+Community%2Doriented+O)
55. Anne Brindle. Genetic Algorithms for Function Optimization. PhD thesis, 1980. [find](https://scholar.google.com/scholar?q=Anne+Brindle%2E+Genetic+Algorithms+for+Function+Optimization%2E+PhD+thesis%2C+1980%2E)
56. David E. Goldberg and Kalyanmoy Deb. A Comparative Analysis of Selection Schemes Used in Genetic Algorithms. In GREGORY J. E. Rawlins, editor, Foundations of Genetic Algorithms, volume 1, pages 69–93. Elsevier, January 1991. [find](https://scholar.google.com/scholar?q=David+E%2E+Goldberg+and+Kalyanmoy+Deb%2E+A+Comparative+Analysis+of+Selection+Schemes+Used+in+Genetic+Algorithms%2E+In+GREGORY+J%2E+E%2E+Rawlins%2C+editor%2C+Foundations+of+Genetic+Algorithms%2C+volume+1%2C+pages+69%E2%80%9393%2E)
57. Esteban Real, Alok Aggarwal, Yanping Huang, and Quoc V. Le. Regularized Evolution for Image Classifier Architecture Search. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01):4780–4789, July 2019. [find](https://scholar.google.com/scholar?q=Esteban+Real%2C+Alok+Aggarwal%2C+Yanping+Huang%2C+and+Quoc+V%2E+Le%2E+Regularized+Evolution+for+Image+Classifier+Architecture+Search%2E+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+33%2801%29%3A4780%E2%80%934)
58. Esteban Real, Chen Liang, David So, and Quoc Le. AutoML-Zero: Evolving Machine Learning Algorithms From Scratch. In International Conference on Machine Learning, pages 8007– 8019. PMLR, November 2020. [find](https://scholar.google.com/scholar?q=Esteban+Real%2C+Chen+Liang%2C+David+So%2C+and+Quoc+Le%2E+AutoML%2DZero%3A+Evolving+Machine+Learning+Algorithms+From+Scratch%2E+In+International+Conference+on+Machine+Learning%2C+pages+8007%E2%80%93+8019%2E+PMLR%2C+November+2020%2E)
59. Gregory S. Hornby. ALPS: The age-layered population structure for reducing the problem of premature convergence. In Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation, GECCO ’06, pages 815– 822, New York, NY, USA, July 2006. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Gregory+S%2E+Hornby%2E+ALPS%3A+The+age%2Dlayered+population+structure+for+reducing+the+problem+of+premature+convergence%2E+In+Proceedings+of+the+8th+Annual+Conference+on+Genetic+and+Evolutionary+Computation%2C+GE)
60. Michael D. Schmidt and Hod Lipson. Age-fitness pareto optimization. In Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation, GECCO ’10, pages 543–544, New York, NY, USA, July 2010. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Michael+D%2E+Schmidt+and+Hod+Lipson%2E+Age%2Dfitness+pareto+optimization%2E+In+Proceedings+of+the+12th+Annual+Conference+on+Genetic+and+Evolutionary+Computation%2C+GECCO+%E2%80%9910%2C+pages+543%E2%80%93544%2C+New+York%2C+NY%2C+USA%2C+J)
61. Miles Cranmer. PySR: Fast & Parallelized Symbolic Regression in Python/Julia. Zenodo, September 2020. [find](https://scholar.google.com/scholar?q=Miles+Cranmer%2E+PySR%3A+Fast+%26+Parallelized+Symbolic+Regression+in+Python%2FJulia%2E+Zenodo%2C+September+2020%2E)
62. S. Kirkpatrick, C. D. Gelatt, and M. P. Vecchi. Optimization by Simulated Annealing. Science, 220:671–680, May 1983. [find](https://scholar.google.com/scholar?q=S%2E+Kirkpatrick%2C+C%2E+D%2E+Gelatt%2C+and+M%2E+P%2E+Vecchi%2E+Optimization+by+Simulated+Annealing%2E+Science%2C+220%3A671%E2%80%93680%2C+May+1983%2E)
63. C. G. Broyden. The convergence of a class of double-rank minimization algorithms 1. General considerations. IMA Journal of Applied Mathematics, 6(1):76–90, March 1970. [find](https://scholar.google.com/scholar?q=C%2E+G%2E+Broyden%2E+The+convergence+of+a+class+of+double%2Drank+minimization+algorithms+1%2E+General+considerations%2E+IMA+Journal+of+Applied+Mathematics%2C+6%281%29%3A76%E2%80%9390%2C+March+1970%2E)
64. Patrick Kofod Mogensen and Asbjørn Nilsen Riseth. Optim: A mathematical optimization package for Julia. Journal of Open Source Software, 3(24):615, 2018. [find](https://scholar.google.com/scholar?q=Patrick+Kofod+Mogensen+and+Asbj%C3%B8rn+Nilsen+Riseth%2E+Optim%3A+A+mathematical+optimization+package+for+Julia%2E+Journal+of+Open+Source+Software%2C+3%2824%29%3A615%2C+2018%2E)
65. Alexander Topchy and W. F. Punch. Faster genetic programming based on local gradient search of numeric leaf values. In Proceedings of the 3rd Annual Conference on Genetic and Evolutionary Computation, GECCO’01, pages 155–162, San Francisco, CA, USA, July 2001. Morgan Kaufmann Publishers Inc. [find](https://scholar.google.com/scholar?q=Alexander+Topchy+and+W%2E+F%2E+Punch%2E+Faster+genetic+programming+based+on+local+gradient+search+of+numeric+leaf+values%2E+In+Proceedings+of+the+3rd+Annual+Conference+on+Genetic+and+Evolutionary+Computation%2C)
66. Fabian Pedregosa, Gaël Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, et al. Scikit-learn: Machine Learning in Python. J. Mach. Learn. Res., 12:2825–2830, November 2011. [find](https://scholar.google.com/scholar?q=Fabian+Pedregosa%2C+Ga%C3%ABl+Varoquaux%2C+Alexandre+Gramfort%2C+Vincent+Michel%2C+Bertrand+Thirion%2C+Olivier+Grisel%2C+Mathieu+Blondel%2C+et+al%2E+Scikit%2Dlearn%3A+Machine+Learning+in+Python%2E+J%2E+Mach%2E+Learn%2E+Res%2E%2C+12%3A2825%E2%80%93)
67. Aaron Meurer, Christopher P. Smith, Mateusz Paprocki, Ondřej Čertík, Sergey B. Kirpichev, Matthew Rocklin, AMiT Kumar, et al. Sympy: symbolic computing in python. PeerJ Computer Science, 3:e103, January 2017. [find](https://scholar.google.com/scholar?q=Aaron+Meurer%2C+Christopher+P%2E+Smith%2C+Mateusz+Paprocki%2C+Ond%C5%99ej+%C4%8Cert%C3%ADk%2C+Sergey+B%2E+Kirpichev%2C+Matthew+Rocklin%2C+AMiT+Kumar%2C+et+al%2E+Sympy%3A+symbolic+computing+in+python%2E+PeerJ+Computer+Science%2C+3%3Ae103%2C+Janua)
68. Charles R. Harris, K. Jarrod Millman, Stéfan J. van der Walt, Ralf Gommers, Pauli Virtanen, David Cournapeau, Eric Wieser, et al. [Array programming with NumPy](https://md.research.elamur.ai/free/en/papers/harris-2020-array-programming-numpy/). Nature, 585(7825):357–362, September 2020.
69. Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, et al. [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://md.research.elamur.ai/free/en/papers/paszke-2019-pytorch-imperative-style-high-performance/). In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett, editors, Advances in Neural Informat…
70. James Bradbury, Roy Frostig, Peter Hawkins, Matthew James Johnson, Chris Leary, Dougal Maclaurin, George Necula, et al. JAX: composable transformations of Python+NumPy programs, 2018. [find](https://scholar.google.com/scholar?q=James+Bradbury%2C+Roy+Frostig%2C+Peter+Hawkins%2C+Matthew+James+Johnson%2C+Chris+Leary%2C+Dougal+Maclaurin%2C+George+Necula%2C+et+al%2E+JAX%3A+composable+transformations+of+Python%2BNumPy+programs%2C+2018%2E)
71. Pablo Lemos, Niall Jeffrey, Miles Cranmer, Peter Battaglia, and Shirley Ho. Rediscovering Newton’s gravity and Solar System properties using deep learning and inductive biases. In submission, 2022. [find](https://scholar.google.com/scholar?q=Pablo+Lemos%2C+Niall+Jeffrey%2C+Miles+Cranmer%2C+Peter+Battaglia%2C+and+Shirley+Ho%2E+Rediscovering+Newton%E2%80%99s+gravity+and+Solar+System+properties+using+deep+learning+and+inductive+biases%2E+In+submission%2C+2022%2E)
72. Léo Grinsztajn, Edouard Oyallon, and Gaël Varoquaux. Why do tree-based models still outperform deep learning on tabular data?, July 2022. [find](https://scholar.google.com/scholar?q=L%C3%A9o+Grinsztajn%2C+Edouard+Oyallon%2C+and+Ga%C3%ABl+Varoquaux%2E+Why+do+tree%2Dbased+models+still+outperform+deep+learning+on+tabular+data%3F%2C+July+2022%2E)
73. Silviu-Marian Udrescu and Max Tegmark. [AI feynman: A physics-inspired method for symbolic regression](https://md.research.elamur.ai/free/en/papers/udrescu-2019-ai-feynman-physics-inspired/). 6(16):eaay2631, 2020. Science Advances,
74. Alan A. Kaptanoglu, Brian M. de Silva, Urban Fasel, Kadierdan Kaheman, Andy J. Goldschmidt, Jared L. Callaham, Charles B. De-lahunt, et al. PySINDy: A comprehensive Python package for robust sparse system identification. November 2021. [find](https://scholar.google.com/scholar?q=Alan+A%2E+Kaptanoglu%2C+Brian+M%2E+de+Silva%2C+Urban+Fasel%2C+Kadierdan+Kaheman%2C+Andy+J%2E+Goldschmidt%2C+Jared+L%2E+Callaham%2C+Charles+B%2E+De%2Dlahunt%2C+et+al%2E+PySINDy%3A+A+comprehensive+Python+package+for+robust+sparse+sy)
75. Kevin René Broløs, Meera Vieira Machado, Chris Cave, Jaan Kasak, Valdemar Stentoft-Hansen, Victor Galindo Batanero, Tom Jelen, and Casper Wilstrup. An Approach to Symbolic Regression Using Feyn. April 2021. [find](https://scholar.google.com/scholar?q=Kevin+Ren%C3%A9+Brol%C3%B8s%2C+Meera+Vieira+Machado%2C+Chris+Cave%2C+Jaan+Kasak%2C+Valdemar+Stentoft%2DHansen%2C+Victor+Galindo+Batanero%2C+Tom+Jelen%2C+and+Casper+Wilstrup%2E+An+Approach+to+Symbolic+Regression+Using+Feyn%2E+April)
76. Nguyen Quang Uy, Nguyen Xuan Hoai, Michael O’Neill, R. I. McKay, and Edgar Galván-López. Semantically-based crossover in genetic programming: Application to real-valued symbolic regression. Genetic Programming and Evolvable Machines, 12(2):91–119, June 2011. [find](https://scholar.google.com/scholar?q=Nguyen+Quang+Uy%2C+Nguyen+Xuan+Hoai%2C+Michael+O%E2%80%99Neill%2C+R%2E+I%2E+McKay%2C+and+Edgar+Galv%C3%A1n%2DL%C3%B3pez%2E+Semantically%2Dbased+crossover+in+genetic+programming%3A+Application+to+real%2Dvalued+symbolic+regression%2E+Genetic+Pr)
77. F. O. de Franca, M. Virgolin, M. Kommenda, M. S. Majumder, M. Cranmer, G. Espada, L. Ingelse, et al. Interpretable Symbolic Regression for Data Science: Analysis of the 2022 Competition, April 2023. [find](https://scholar.google.com/scholar?q=F%2E+O%2E+de+Franca%2C+M%2E+Virgolin%2C+M%2E+Kommenda%2C+M%2E+S%2E+Majumder%2C+M%2E+Cranmer%2C+G%2E+Espada%2C+L%2E+Ingelse%2C+et+al%2E+Interpretable+Symbolic+Regression+for+Data+Science%3A+Analysis+of+the+2022+Competition%2C+April+2023%2E)
78. Ankit Rohatgi. Webplotdigitizer: Version 4.6, 2022. [find](https://scholar.google.com/scholar?q=Ankit+Rohatgi%2E+Webplotdigitizer%3A+Version+4%2E6%2C+2022%2E)
79. Edwin Hubble. A relation between distance and radial velocity among extra-galactic nebulae. Proceedings of the National Academy of Sciences, 15(3):168–173, March 1929. [find](https://scholar.google.com/scholar?q=Edwin+Hubble%2E+A+relation+between+distance+and+radial+velocity+among+extra%2Dgalactic+nebulae%2E+Proceedings+of+the+National+Academy+of+Sciences%2C+15%283%29%3A168%E2%80%93173%2C+March+1929%2E)
80. William La Cava, Patryk Orzechowski, Bogdan Burlacu, Fabrício Olivetti de França, Marco Virgolin, Ying Jin, Michael Kommenda, and Jason H. Moore. [Contemporary Symbolic Regression Methods and their Relative Performance](https://md.research.elamur.ai/free/en/papers/cava-2021-contemporary-symbolic-regression-methods/), July 2021.
81. Johannes Kepler. Harmonices Mundi. Lincii Austriæ, 1619. [find](https://scholar.google.com/scholar?q=Johannes+Kepler%2E+Harmonices+Mundi%2E+Lincii+Austri%C3%A6%2C+1619%2E)
82. Isaac Newton. Philosophiæ Naturalis Principia Mathematica. Jussu Societatis Regiæ ac Typis Joseph Streater, London, England, 1687. [find](https://scholar.google.com/scholar?q=Isaac+Newton%2E+Philosophi%C3%A6+Naturalis+Principia+Mathematica%2E+Jussu+Societatis+Regi%C3%A6+ac+Typis+Joseph+Streater%2C+London%2C+England%2C+1687%2E)
83. Max Planck. The Theory of Heat Radiation. P. Blakiston’s Son & Co, Philadelphia, 1914. [find](https://scholar.google.com/scholar?q=Max+Planck%2E+The+Theory+of+Heat+Radiation%2E+P%2E+Blakiston%E2%80%99s+Son+%26+Co%2C+Philadelphia%2C+1914%2E)
84. Henrietta S. Leavitt and Edward C. Pickering. Periods of 25 Variable Stars in the Small Magel-lanic Cloud. Harvard College Observatory Circular, 173:1–3, March 1912. [find](https://scholar.google.com/scholar?q=Henrietta+S%2E+Leavitt+and+Edward+C%2E+Pickering%2E+Periods+of+25+Variable+Stars+in+the+Small+Magel%2Dlanic+Cloud%2E+Harvard+College+Observatory+Circular%2C+173%3A1%E2%80%933%2C+March+1912%2E)
85. William H. Press and Paul Schechter. Formation of Galaxies and Clusters of Galaxies by Self-Similar Gravitational Condensation. The Astrophysical Journal, 187:425–438, February 1974. [find](https://scholar.google.com/scholar?q=William+H%2E+Press+and+Paul+Schechter%2E+Formation+of+Galaxies+and+Clusters+of+Galaxies+by+Self%2DSimilar+Gravitational+Condensation%2E+The+Astrophysical+Journal%2C+187%3A425%E2%80%93438%2C+February+1974%2E)
86. Charles Bonnet. Contemplation de La Nature. Amsterdam, 1764. [find](https://scholar.google.com/scholar?q=Charles+Bonnet%2E+Contemplation+de+La+Nature%2E+Amsterdam%2C+1764%2E)
87. Émile Clapeyron. Mémoire sur la puissance motrice de la chaleur. Journal de l’École Polytechnique, 1835. [find](https://scholar.google.com/scholar?q=%C3%89mile+Clapeyron%2E+M%C3%A9moire+sur+la+puissance+motrice+de+la+chaleur%2E+Journal+de+l%E2%80%99%C3%89cole+Polytechnique%2C+1835%2E)
88. Johannes Rydberg. Researches sur la constitution des spectres d’émission des Éléments chimiques. Proceedings of the Royal Swedish Academy of Science, 1889. [find](https://scholar.google.com/scholar?q=Johannes+Rydberg%2E+Researches+sur+la+constitution+des+spectres+d%E2%80%99%C3%A9mission+des+%C3%89l%C3%A9ments+chimiques%2E+Proceedings+of+the+Royal+Swedish+Academy+of+Science%2C+1889%2E)
89. Arthur Grundner, Tom Beucler, Pierre Gen-tine, and Veronika Eyring. Data-Driven Equation Discovery of a Cloud Cover Parameterization, April 2023. [find](https://scholar.google.com/scholar?q=Arthur+Grundner%2C+Tom+Beucler%2C+Pierre+Gen%2Dtine%2C+and+Veronika+Eyring%2E+Data%2DDriven+Equation+Discovery+of+a+Cloud+Cover+Parameterization%2C+April+2023%2E)
90. Yanzhang Li, Hongyu Wang, Yan Li, Huan Ye, Yanan Zhang, Rongzhang Yin, Haoning Jia, et al. Electron transfer rules of minerals under pressure informed by machine learning. Nature Communications, 14(1):1815, March 2023. [find](https://scholar.google.com/scholar?q=Yanzhang+Li%2C+Hongyu+Wang%2C+Yan+Li%2C+Huan+Ye%2C+Yanan+Zhang%2C+Rongzhang+Yin%2C+Haoning+Jia%2C+et+al%2E+Electron+transfer+rules+of+minerals+under+pressure+informed+by+machine+learning%2E+Nature+Communications%2C+14%281%29)
91. Konstantin T. Matchev, Katia Matcheva, and Alexander Roman. Analytical Modeling of Exoplanet Transit Spectroscopy with Dimensional Analysis and Symbolic Regression. The Astrophysical Journal, 930(1):33, May 2022. [find](https://scholar.google.com/scholar?q=Konstantin+T%2E+Matchev%2C+Katia+Matcheva%2C+and+Alexander+Roman%2E+Analytical+Modeling+of+Exoplanet+Transit+Spectroscopy+with+Dimensional+Analysis+and+Symbolic+Regression%2E+The+Astrophysical+Journal%2C+930%281%29%3A3)
92. Digvijay Wadekar, Leander Thiele, J. Colin Hill, Shivam Pandey, Francisco Villaescusa-Navarro, David N. Spergel, Miles Cranmer, et al. The SZ flux-mass (Y-M) relation at low halo masses: Improvements with symbolic regression and strong constraints on baryonic feedback. September 2022. [find](https://scholar.google.com/scholar?q=Digvijay+Wadekar%2C+Leander+Thiele%2C+J%2E+Colin+Hill%2C+Shivam+Pandey%2C+Francisco+Villaescusa%2DNavarro%2C+David+N%2E+Spergel%2C+Miles+Cranmer%2C+et+al%2E+The+SZ+flux%2Dmass+%28Y%2DM%29+relation+at+low+halo+masses%3A+Improvements+)
93. Digvijay Wadekar, Leander Thiele, Francisco Villaescusa-Navarro, J. Colin Hill, Miles Cranmer, David N. Spergel, Nicholas Battaglia, et al. Augmenting astrophysical scaling rela- [104] Michael Droettboom, John Hunter, Thomas A Caswell, Eric Firing, Jens Hedegaard Nielsen, tions with machine learning… [find](https://scholar.google.com/scholar?q=Digvijay+Wadekar%2C+Leander+Thiele%2C+Francisco+Villaescusa%2DNavarro%2C+J%2E+Colin+Hill%2C+Miles+Cranmer%2C+David+N%2E+Spergel%2C+Nicholas+Battaglia%2C+et+al%2E+Augmenting+astrophysical+scaling+rela%2D+%5B104%5D+Michael+Droettb)
94. Sergiy Verstyuk and Michael R. Douglas. Machine Learning the Gravity Equation for Inter- [105] Rodrigo Luger and Contributors. Showyourwork!, 2021. national Trade. SSRN Electronic Journal, 2022. [find](https://scholar.google.com/scholar?q=Sergiy+Verstyuk+and+Michael+R%2E+Douglas%2E+Machine+Learning+the+Gravity+Equation+for+Inter%2D+%5B105%5D+Rodrigo+Luger+and+Contributors%2E+Showyourwork%21%2C+2021%2E+national+Trade%2E+SSRN+Electronic+Journal%2C+2022%2E)
95. Patrick Kidger. On Neural Differential Equa- [106] Charlie Wood. Powerful ‘Machine Scientists’ Distill the Laws of Physics From Raw Data. tions, February 2022. Quanta Magazine, May 2022. [find](https://scholar.google.com/scholar?q=Patrick+Kidger%2E+On+Neural+Differential+Equa%2D+%5B106%5D+Charlie+Wood%2E+Powerful+%E2%80%98Machine+Scientists%E2%80%99+Distill+the+Laws+of+Physics+From+Raw+Data%2E+tions%2C+February+2022%2E+Quanta+Magazine%2C+May+2022%2E)
96. Kaze W. K. Wong and Miles Cranmer. Automated discovery of interpretable gravitational-wave population models. ML4Astro Workshop @ ICML 2022, July 2022. [find](https://scholar.google.com/scholar?q=Kaze+W%2E+K%2E+Wong+and+Miles+Cranmer%2E+Automated+discovery+of+interpretable+gravitational%2Dwave+population+models%2E+ML4Astro+Workshop+%40+ICML+2022%2C+July+2022%2E)
97. Guido Van Rossum and Fred L. Drake. Python 3 Reference Manual. CreateSpace, Scotts Valley, CA, 2009. [find](https://scholar.google.com/scholar?q=Guido+Van+Rossum+and+Fred+L%2E+Drake%2E+Python+3+Reference+Manual%2E+CreateSpace%2C+Scotts+Valley%2C+CA%2C+2009%2E)
98. Jeff Bezanson, Alan Edelman, Stefan Karpinski, and Viral B. Shah. Julia: A Fresh Approach to Numerical Computing. arXiv:1411.1607 [cs], July 2015. [find](https://scholar.google.com/scholar?q=Jeff+Bezanson%2C+Alan+Edelman%2C+Stefan+Karpinski%2C+and+Viral+B%2E+Shah%2E+Julia%3A+A+Fresh+Approach+to+Numerical+Computing%2E+arXiv%3A1411%2E1607+%5Bcs%5D%2C+July+2015%2E)
99. Fabian Pedregosa, Gaël Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, et al. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12(85):2825–2830, 2011. [find](https://scholar.google.com/scholar?q=Fabian+Pedregosa%2C+Ga%C3%ABl+Varoquaux%2C+Alexandre+Gramfort%2C+Vincent+Michel%2C+Bertrand+Thirion%2C+Olivier+Grisel%2C+Mathieu+Blondel%2C+et+al%2E+Scikit%2Dlearn%3A+Machine+Learning+in+Python%2E+Journal+of+Machine+Learning+Re)
100. Wes McKinney. [Data Structures for Statistical Computing in Python](https://md.research.elamur.ai/free/en/papers/mckinney-2010-data-structures-statistical-computing-python/). In Stéfan van der Walt and Jarrod Millman, editors, Proceedings of the 9th Python in Science Conference, pages 56 – 61, 2010.
101. Chris Elrod. LoopVectorization.jl: Macro(s) for vectorizing loops. JuliaHub, 2022. [find](https://scholar.google.com/scholar?q=Chris+Elrod%2E+LoopVectorization%2Ejl%3A+Macro%28s%29+for+vectorizing+loops%2E+JuliaHub%2C+2022%2E)
102. Michael Innes. Don’t unroll adjoint: Differentiating SSA-Form programs. CoRR, abs/1810.07951, 2018. — [arXiv:1810.07951](https://arxiv.org/abs/1810.07951) [find](https://scholar.google.com/scholar?q=Michael+Innes%2E+Don%E2%80%99t+unroll+adjoint%3A+Differentiating+SSA%2DForm+programs%2E+CoRR%2C+abs%2F1810%2E07951%2C+2018%2E+%E2%80%94+%5BarXiv%3A1810%2E07951%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1810%2E07951%29)
103. Shashi Gowda, Yingbo Ma, Alessandro Cheli, Maja Gwóźzdź, Viral B. Shah, Alan Edelman, and Christopher Rackauckas. High-performance symbolic-numerics via multiple dispatch. ACM Communications in Computer Algebra, 55(3):92–96, January 2022. [find](https://scholar.google.com/scholar?q=Shashi+Gowda%2C+Yingbo+Ma%2C+Alessandro+Cheli%2C+Maja+Gw%C3%B3%C5%BAzd%C5%BA%2C+Viral+B%2E+Shah%2C+Alan+Edelman%2C+and+Christopher+Rackauckas%2E+High%2Dperformance+symbolic%2Dnumerics+via+multiple+dispatch%2E+ACM+Communications+in+Comput)

*Updated 3 November 2026*