The recently developed matrix based Renyi's entropy enables measurement of information in data simply using the eigenspectrum of symmetric positive semi definite (PSD) matrices in reproducing kernel Hilbert space, without estimation of the underlying data distribution. This intriguing property makes the new information measurement widely adopted in multiple statistical inference and learning tasks. However, the computation of such quantity involves the trace operator on a PSD matrix $G$ to power $\alpha$(i.e., $tr(G^\alpha)$), with a normal complexity of nearly $O(n^3)$, which severely hampers its practical usage when the number of samples (i.e., $n$) is large. In this work, we present computationally efficient approximations to this new entropy functional that can reduce its complexity to even significantly less than $O(n^2)$. To this end, we leverage the recent progress on Randomized Numerical Linear Algebra, developing Taylor, Chebyshev and Lanczos approximations to $tr(G^\alpha)$ for arbitrary values of $\alpha$ by converting it into matrix-vector multiplications problem. We also establish the connection between the matrix-based Renyi's entropy and PSD matrix approximation, which enables exploiting both clustering and block low-rank structure of $G$ to further reduce the computational cost. We theoretically provide approximation accuracy guarantees and illustrate the properties of different approximations. Large-scale experimental evaluations on both synthetic and real-world data corroborate our theoretical findings, showing promising speedup with negligible loss in accuracy.
翻译:最近开发的基于Renyi 的矩阵使得能够测量数据中的信息,只是利用对正半确定(PSD)矩阵的正正正正正正正正正正正半确定(PSD)矩阵来复制核心的Hilbert空间,而没有估算基本数据分布。这种令人感兴趣的属性使得新的信息测量在多重统计推理和学习任务中广泛采用。然而,这种数量的计算涉及一个私营部门司基矩阵的追踪操作员,即G$G$至alpha$(即,G$tr(Gäalpha)美元),通常的复杂程度近于O(n)3美元,当样本数量(即美元)很大时,这严重妨碍了其实际使用。在这项工作中,我们为这个新的英美化功能提供了计算效率的近似近似近似近似值,可以将其复杂性降到甚至大大低于$O(n&2)美元。为此,我们开发了Nummericalal Linebrala Algebra, 和 Lanczos 将它的正al-ral-ralallialalalalalalal-ralalal-ral-ralalal-ralalalalalal-rational-rational-rational-lations, rational-rational-rational-rational-rations bal-rations bal-rations nual-rations bal-rational-rations bal-rations bal-rational-rational-rational-rational-rational-s bal-s bal-rational-s bal-s bal-rational-rational-rations bal-s bal-s bal-sal-s bal)。