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 1706.07883math.NAcs.NA
收藏

关于高维中径向基函数核的数值秩

On the numerical rank of radial basis function kernels in high dimension

Stanford University(斯坦福大学);Duke University(杜克大学)

Ruoxi Wang, Yingzhou Li, Eric Darve

AI总结:

本文研究了高维数据中径向基函数核的数值秩,通过分析核矩阵的秩上界,提出了低秩近似方法,并给出了函数秩和L∞误差的显式上界,通过理论分析和实验验证了结果。

摘要:

低秩近似是减少大规模核矩阵算法高计算成本的流行方法。低秩方法的成功依赖于核矩阵的矩阵秩,在实践中,这些方法即使在高维数据集上也有效。这种实际成功促使我们分析函数秩,即矩阵秩的上界。在本文中,我们考虑径向基函数(RBF),用低秩表示近似RBF核,该表示是有限和的分离积,并为这样的近似提供了函数秩和L∞误差的显式上界。我们的三个主要结果如下。首先,对于固定的精度,RBF的函数秩在最坏情况下与数据维度呈多项式增长。其次,精确的低秩近似在L∞范数下的误差界以函数光滑性和域直径为函数。最后,观察到RBF核矩阵奇异值幅度的群模式,并分析并解释了这种模式,通过核的低秩表示中项的分组来解释。实验证果验证了理论结果。

英文摘要:

Low-rank approximations are popular methods to reduce the high computational cost of algorithms involving large-scale kernel matrices. The success of low-rank methods hinges on the matrix rank of the kernel matrix, and in practice, these methods are effective even for high-dimensional datasets. Their practical success motivates our analysis of the function rank, an upper bound of the matrix rank. In this paper, we consider radial basis functions (RBF), approximate the RBF kernel with a low-rank representation that is a finite sum of separate products and provide explicit upper bounds on the function rank and the $L_\infty$ error for such approximations. Our three main results are as follows. First, for a fixed precision, the function rank of RBFs, in the worst case, grows polynomially with the data dimension. Second, precise error bounds for the low-rank approximations in the $L_\infty$ norm are derived in terms of the function smoothness and the domain diameters. Finally, a group pattern in the magnitude of singular values for RBF kernel matrices is observed and analyzed, and is explained by a grouping of the expansion terms in the kernel's low-rank representation. Empirical results verify the theoretical results.

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。

↑