Neural networks' expressiveness comes at the cost of complex, black-box models that often extrapolate poorly beyond the domain of the training dataset, conflicting with the goal of finding compact analytic expressions to describe scientific data. We introduce OccamNet, a neural network model that finds interpretable, compact, and sparse symbolic fits to data, \`a la Occam's razor. Our model defines a probability distribution over functions with efficient sampling and function evaluation. We train by sampling functions and biasing the probability mass toward better fitting solutions, backpropagating using cross-entropy matching in a reinforcement-learning loss. OccamNet can identify symbolic fits for a variety of problems, including analytic and non-analytic functions, implicit functions, and simple image classification, and can outperform state-of-the-art symbolic regression methods on real-world regression datasets. Our method requires a minimal memory footprint, fits complicated functions in minutes on a single CPU, and scales on a GPU.
@article{arxiv.2007.10784,
title = {OccamNet: A Fast Neural Model for Symbolic Regression at Scale},
author = {Owen Dugan and Rumen Dangovski and Allan Costa and Samuel Kim and Pawan Goyal and Joseph Jacobson and Marin Soljačić},
journal= {arXiv preprint arXiv:2007.10784},
year = {2023}
}