arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.03474cs.LG
收藏

可伸缩核方法的随机Gegenbauer特征

Random Gegenbauer Features for Scalable Kernel Methods

Yale University(耶鲁大学);MPI-Informatics(马克斯·普朗克信息学研究所);Tel Aviv University(特拉维夫大学)

Insu Han, Amir Zandieh, Haim Avron

摘要:

我们提出了有效的随机功能,近似一个新的和丰富的核函数,我们称为广义带状核(GZK)。我们提出的GZK家族,概括了区域内核(即,单位球面上的点积核),并且包括广泛的普遍存在的核函数,诸如点积核的整体以及高斯核和最近引入的神经切线核。有趣的是,通过利用Gegenbauer多项式的再生特性,我们可以基于随机定向的Gegenbauer核为GZK族构造有效的随机特征。我们证明子空间嵌入保证我们的Gegenbauer功能,确保我们的功能可以用于近似解决学习问题,如核k-均值聚类,核岭回归等经验结果表明,我们提出的功能优于最近的核近似方法。

英文摘要:

We propose efficient random features for approximating a new and rich class of kernel functions that we refer to as Generalized Zonal Kernels (GZK). Our proposed GZK family, generalizes the zonal kernels (i.e., dot-product kernels on the unit sphere) by introducing radial factors in their Gegenbauer series expansion, and includes a wide range of ubiquitous kernel functions such as the entirety of dot-product kernels as well as the Gaussian and the recently introduced Neural Tangent kernels. Interestingly, by exploiting the reproducing property of the Gegenbauer polynomials, we can construct efficient random features for the GZK family based on randomly oriented Gegenbauer kernels. We prove subspace embedding guarantees for our Gegenbauer features which ensures that our features can be used for approximately solving learning problems such as kernel k-means clustering, kernel ridge regression, etc. Empirical results show that our proposed features outperform recent kernel approximation methods.

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。

↑