A major challenge in applying machine learning to automated theorem proving is the scarcity of training data, which is a key ingredient in training successful deep learning models. To tackle this problem, we propose an approach that relies on training purely with synthetically generated theorems, without any human data aside from axioms. We use these theorems to train a neurally-guided saturation-based prover. Our neural prover outperforms the state-of-the-art E-prover on this synthetic data in both time and search steps, and shows significant transfer to the unseen human-written theorems from the TPTP library, where it solves 72\% of first-order problems without equality.
@article{arxiv.2103.03798,
title = {Training a First-Order Theorem Prover from Synthetic Data},
author = {Vlad Firoiu and Eser Aygun and Ankit Anand and Zafarali Ahmed and Xavier Glorot and Laurent Orseau and Lei Zhang and Doina Precup and Shibl Mourad},
journal= {arXiv preprint arXiv:2103.03798},
year = {2021}
}