arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2308.09474cs.AIcs.SCmath.OC
收藏

通过AI Hilbert统一数据与背景知识推动科学发现演进

Evolving Scientific Discovery by Unifying Data and Background Knowledge with AI Hilbert

Imperial College Business School(帝国理工商学院);Samsung AI(三星人工智能);IBM Thomas J. Watson Research Center(IBM托马斯·J·沃森研究中心)

Ryan Cory-Wright, Cristina Cornelio, Sanjeeb Dash, Bachir El Khadir, Lior Horesh

AI总结:

针对数据驱动科学发现在噪声或稀缺数据下失效、且与背景理论一致的公式搜索问题,提出AI Hilbert方法,结合多项式优化与正点定理,可从公理和数据中有效推导经典科学定律。

摘要:

发现能够简洁解释自然现象且与现有背景理论相符的科学公式是科学的核心目标。历史上,科学家们通过基于现有知识推导方程、构建新方程并通过实验验证来得出自然定律。近年来,数据驱动的科学发现在拥有大量实验数据的场景中已成为一种可行的替代路径。但遗憾的是,当数据存在噪声或数据稀缺时,数据驱动方法往往无法发现有效的定律。为此,近期的研究将回归与推理相结合,以剔除与背景理论不一致的公式。然而,在与背景理论一致的公式空间中进行搜索,以找到最契合数据的公式这一问题仍未得到妥善解决。我们针对所有公理和科学定律均可通过多项式等式与不等式表达的场景提出了一种解决方案,并认为我们的方法具有广泛的适用性。我们使用二元变量和逻辑约束对最小复杂度的概念进行建模,通过混合整数线性或半定优化求解多项式优化问题,并利用Positivstellensatz(正点定理)证书以有原则的方式证明我们的科学发现的有效性。本文采用的优化技术使得我们的方法在推导复杂度有界的假设下,搭配完全正确的背景理论时可在多项式时间内运行,而在背景理论部分正确时则以非确定性多项式(NP)时间运行。我们证明,包括开普勒行星运动第三定律、哈根-泊肃叶方程以及辐射引力波功率方程在内的一些著名科学定律,都可以从公理和实验数据中有原则地推导出来。

英文摘要:

The discovery of scientific formulae that parsimoniously explain natural phenomena and align with existing background theory is a key goal in science. Historically, scientists have derived natural laws by manipulating equations based on existing knowledge, forming new equations, and verifying them experimentally. In recent years, data-driven scientific discovery has emerged as a viable competitor in settings with large amounts of experimental data. Unfortunately, data-driven methods often fail to discover valid laws when data is noisy or scarce. Accordingly, recent works combine regression and reasoning to eliminate formulae inconsistent with background theory. However, the problem of searching over the space of formulae consistent with background theory to find one that best fits the data is not well-solved. We propose a solution to this problem when all axioms and scientific laws are expressible via polynomial equalities and inequalities and argue that our approach is widely applicable. We model notions of minimal complexity using binary variables and logical constraints, solve polynomial optimization problems via mixed-integer linear or semidefinite optimization, and prove the validity of our scientific discoveries in a principled manner using Positivstellensatz certificates. The optimization techniques leveraged in this paper allow our approach to run in polynomial time with fully correct background theory under an assumption that the complexity of our derivation is bounded), or non-deterministic polynomial (NP) time with partially correct background theory. We demonstrate that some famous scientific laws, including Kepler's Third Law of Planetary Motion, the Hagen-Poiseuille Equation, and the Radiated Gravitational Wave Power equation, can be derived in a principled manner from axioms and experimental data.

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。

↑