代数簇上的核近似
Kernel approximation on algebraic varieties
AI总结:
针对限制在代数簇上的光滑各向同性核,论文用多项式核近似并利用其降秩与最大值性质,证明所需秩取决于簇维数而非环境维数。
摘要:
核的低秩近似是一个基础数学问题,具有广泛的算法应用。核通常被限制在代数簇上,例如在涉及稀疏或低秩数据的问题中。我们证明,在这种设定下可以获得显著更好的近似:达到给定误差所需的秩取决于簇的维数,而不是通常大得多的环境维数。这在高精度和高维两种情形下都成立。我们的结果针对光滑各向同性核给出,这是应用中使用的主要核类别。我们的主要技术洞见是用多项式核近似光滑核,并利用多项式核在被限制到簇上时成立的两个关键性质。第一,它们的秩随簇的余维数呈指数下降。第二,它们的最大值由其在一小组点上的值所控制。总之,我们的结果提供了一种利用数据集中(近似)“代数结构”以高效解决大规模数据科学问题的通用方法。
英文摘要:
Low-rank approximation of kernels is a fundamental mathematical problem with widespread algorithmic applications. Often the kernel is restricted to an algebraic variety, e.g., in problems involving sparse or low-rank data. We show that significantly better approximations are obtainable in this setting: the rank required to achieve a given error depends on the variety's dimension rather than the ambient dimension, which is typically much larger. This is true in both high-precision and high-dimensional regimes. Our results are presented for smooth isotropic kernels, the predominant class of kernels used in applications. Our main technical insight is to approximate smooth kernels by polynomial kernels, and leverage two key properties of polynomial kernels that hold when they are restricted to a variety. First, their ranks decrease exponentially in the variety's co-dimension. Second, their maximum values are governed by their values over a small set of points. Together, our results provide a general approach for exploiting (approximate) "algebraic structure" in datasets in order to efficiently solve large-scale data science problems.
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。