arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1906.01681cs.LGcs.CCmath.OCstat.ML
收藏

学习动态多项式证明

Learning dynamic polynomial proofs

DeepMind(深度思维);University of Cambridge(剑桥大学);ENS Lyon(里昂高等师范学院)

Alhussein Fawzi, Mateusz Malinowski, Hamza Fawzi, Omar Fawzi

摘要:

多项式不等式是许多数学学科的核心。在本文中,我们认为自动搜索证明多项式不等式的基本计算任务。我们采用半代数证明系统的框架,通过基本的推理规则,推断新的不平等的前提下,操纵多项式不等式。这些证明系统被认为是非常强大的,但寻找证明仍然是一个主要的困难。在这项工作中,我们引入了一个基于机器学习的方法来搜索这些证明系统中的动态证明。我们提出了一个深度强化学习框架,它学习多项式的嵌入并指导推理规则的选择,将问题的固有对称性视为归纳偏差。我们将我们的方法与基于静态证明系统的强大且广泛研究的线性规划层次结构进行比较,并表明我们的方法将线性规划的大小降低了几个数量级,同时还提高了性能。因此,这些结果铺平了道路,以增强强大的和良好的研究半代数证明系统与机器学习指导策略,以提高这种证明系统的表达能力。

英文摘要:

Polynomial inequalities lie at the heart of many mathematical disciplines. In this paper, we consider the fundamental computational task of automatically searching for proofs of polynomial inequalities. We adopt the framework of semi-algebraic proof systems that manipulate polynomial inequalities via elementary inference rules that infer new inequalities from the premises. These proof systems are known to be very powerful, but searching for proofs remains a major difficulty. In this work, we introduce a machine learning based method to search for a dynamic proof within these proof systems. We propose a deep reinforcement learning framework that learns an embedding of the polynomials and guides the choice of inference rules, taking the inherent symmetries of the problem as an inductive bias. We compare our approach with powerful and widely-studied linear programming hierarchies based on static proof systems, and show that our method reduces the size of the linear program by several orders of magnitude while also improving performance. These results hence pave the way towards augmenting powerful and well-studied semi-algebraic proof systems with machine learning guiding strategies for enhancing the expressivity of such proof systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑