Timezone: »
Poster
Learning to Prove Theorems by Learning to Generate Theorems
Mingzhe Wang · Jia Deng
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.
Author Information
Mingzhe Wang (Pinceton University)
Jia Deng (Princeton University)
More from the Same Authors
-
2021 Oral: DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras »
Zachary Teed · Jia Deng -
2021 Poster: DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras »
Zachary Teed · Jia Deng -
2020 Poster: Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D »
Ankit Goyal · Kaiyu Yang · Dawei Yang · Jia Deng -
2020 Spotlight: Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D »
Ankit Goyal · Kaiyu Yang · Dawei Yang · Jia Deng -
2020 Poster: Strongly Incremental Constituency Parsing with Graph Neural Networks »
Kaiyu Yang · Jia Deng -
2011 Poster: Fast and Balanced: Efficient Label Tree Learning for Large Scale Object Recognition »
Jia Deng · Sanjeev Satheesh · Alexander C Berg · Li Fei-Fei