Timezone: »
We present an environment, benchmark, and deep learning driven automated theorem prover for higher-order logic. Higher-order interactive theorem provers enable the formalization of arbitrary mathematical theories and thereby present an interesting challenge for deep learning. We provide an open-source framework based on the HOL Light theorem prover that can be used as a reinforcement learning environment. HOL Light comes with a broad coverage of basic mathematical theorems on calculus and the formal proof of the Kepler conjecture, from which we derive a challenging benchmark for automated reasoning approaches. We also present a deep reinforcement learning driven automated theorem prover, DeepHOL, that gives strong initial results on this benchmark.
Author Information
Kshitij Bansal (Google Research)
Sarah Loos (Google)
Markus Rabe (Google)
Christian Szegedy (Google)
Stewart Wilcox (Googl)
Related Events (a corresponding poster, oral, or spotlight)
-
2019 Oral: HOList: An Environment for Machine Learning of Higher Order Logic Theorem Proving »
Tue. Jun 11th 06:35 -- 06:40 PM Room Room 201
More from the Same Authors
-
2021 Poster: LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning »
Yuhuai Wu · Markus Rabe · Wenda Li · Jimmy Ba · Roger Grosse · Christian Szegedy -
2021 Spotlight: LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning »
Yuhuai Wu · Markus Rabe · Wenda Li · Jimmy Ba · Roger Grosse · Christian Szegedy