Learning to Prove Theorems by Learning to Generate Theorems
Abstract
We consider the task of automated theorem proving, a key AI task. Deep learning has shown promise for training theorem provers, but there are limited human-written theorems and proofs available for supervised learning. To address this limitation, we propose to learn a neural generator that automatically synthesizes theorems and proofs for the purpose of training a theorem prover. Experiments on real-world tasks demonstrate that synthetic data from our approach improves the theorem prover and advances the state of the art of automated theorem proving in Metamath.
Cite
Text
Wang and Deng. "Learning to Prove Theorems by Learning to Generate Theorems." Neural Information Processing Systems, 2020.Markdown
[Wang and Deng. "Learning to Prove Theorems by Learning to Generate Theorems." Neural Information Processing Systems, 2020.](https://mlanthology.org/neurips/2020/wang2020neurips-learning/)BibTeX
@inproceedings{wang2020neurips-learning,
title = {{Learning to Prove Theorems by Learning to Generate Theorems}},
author = {Wang, Mingzhe and Deng, Jia},
booktitle = {Neural Information Processing Systems},
year = {2020},
url = {https://mlanthology.org/neurips/2020/wang2020neurips-learning/}
}