ICML 2022spotlight29 citations

Deep symbolic regression for recurrence prediction

Stéphane D’Ascoli, Pierre-Alexandre Kamienny, Guillaume Lample, Francois Charton

Abstract

Symbolic regression, i.e. predicting a function from the observation of its values, is well-known to be a challenging task. In this paper, we train Transformers to infer the function or recurrence relation underlying sequences of integers or floats, a typical task in human IQ tests which has hardly been tackled in the machine learning literature. We evaluate our integer model on a subset of OEIS sequences, and show that it outperforms built-in Mathematica functions for recurrence prediction. We also demonstrate that our float model is able to yield informative approximations of out-of-vocabulary functions and constants, e.g. $\operatorname{bessel0}(x)\approx \frac{\sin(x)+\cos(x)}{\sqrt{\pi x}}$ and $1.644934\approx \pi^2/6$.

BibTeX
@InProceedings{pmlr-v162-d-ascoli22a,
  title = 	 {Deep symbolic regression for recurrence prediction},
  author =       {D'Ascoli, St{\'e}phane and Kamienny, Pierre-Alexandre and Lample, Guillaume and Charton, Francois},
  booktitle = 	 {Proceedings of the 39th International Conference on Machine Learning},
  pages = 	 {4520--4536},
  year = 	 {2022},
  editor = 	 {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
  volume = 	 {162},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {17--23 Jul},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v162/d-ascoli22a/d-ascoli22a.pdf},
  url = 	 {https://proceedings.mlr.press/v162/d-ascoli22a.html},
  abstract = 	 {Symbolic regression, i.e. predicting a function from the observation of its values, is well-known to be a challenging task. In this paper, we train Transformers to infer the function or recurrence relation underlying sequences of integers or floats, a typical task in human IQ tests which has hardly been tackled in the machine learning literature. We evaluate our integer model on a subset of OEIS sequences, and show that it outperforms built-in Mathematica functions for recurrence prediction. We also demonstrate that our float model is able to yield informative approximations of out-of-vocabulary functions and constants, e.g. $\operatorname{bessel0}(x)\approx \frac{\sin(x)+\cos(x)}{\sqrt{\pi x}}$ and $1.644934\approx \pi^2/6$.}
}