INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving

Autor:	Wu, Yuhuai, Jiang, Albert Qiaochu, Ba, Jimmy, Grosse, Roger
Rok vydání:	2020
Předmět:	Computer Science - Artificial Intelligence Computer Science - Machine Learning Computer Science - Logic in Computer Science Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	In learning-assisted theorem proving, one of the most critical challenges is to generalize to theorems unlike those seen at training time. In this paper, we introduce INT, an INequality Theorem proving benchmark, specifically designed to test agents' generalization ability. INT is based on a procedure for generating theorems and proofs; this procedure's knobs allow us to measure 6 different types of generalization, each reflecting a distinct challenge characteristic to automated theorem proving. In addition, unlike prior benchmarks for learning-assisted theorem proving, INT provides a lightweight and user-friendly theorem proving environment with fast simulations, conducive to performing learning-based and search-based research. We introduce learning-based baselines and evaluate them across 6 dimensions of generalization with the benchmark. We then evaluate the same agents augmented with Monte Carlo Tree Search (MCTS) at test time, and show that MCTS can help to prove new theorems. Comment: Published as a conference paper at ICLR 2021
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2007.02924 Zobrazit plný text záznamu View this record from Arxiv