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 2404.02639physics.chem-ph
收藏

通过重加权扩散映射选择物理系统的高维表示

Selecting High-Dimensional Representations of Physical Systems by Reweighted Diffusion Maps

Jakub Rydzewski

AI总结:

针对降维前高维表示选择被忽视的问题,本文提出利用 reweighted diffusion map 分析原子模拟数据中 Markov 转移矩阵的谱分解,实现高维表示的定量选择,并通过多个高维示例验证其性能。

摘要:

构建高维系统的约化表示是物理化学中的一个基本问题。许多无监督机器学习方法能够自动找到此类低维表示。然而,一个常被忽视的问题是,在降维之前应当使用何种高维表示来描述系统。本文中,我们利用一种近期开发的、名为 reweighted diffusion map(重加权扩散映射)的方法来解决这一问题[J. Chem. Theory Comput. 2022, 18, 7179-7192]。我们展示了如何通过探究由标准或增强采样原子模拟所得数据构建的 Markov 转移矩阵的谱分解,来定量选择高维表示。我们在若干高维示例中证明了该方法的性能。

英文摘要:

Constructing reduced representations of high-dimensional systems is a fundamental problem in physical chemistry. Many unsupervised machine learning methods can automatically find such low-dimensional representations. However, an often overlooked problem is what high-dimensional representation should be used to describe systems before dimensionality reduction. Here, we address this issue using a recently developed method called reweighted diffusion map [J. Chem. Theory Comput. 2022, 18, 7179-7192]. We show how high-dimensional representations can be quantitatively selected by exploring the spectral decomposition of Markov transition matrices built from data obtained from standard or enhanced sampling atomistic simulations. We demonstrate the performance of the method in several high-dimensional examples.

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。

↑