Approximate Kernel PCA Using Random Features: Computational vs. Statistical Trade-off

Abstract

Kernel methods are powerful learning methodologies that allow to perform non-linear data analysis. Despite their popularity, they suffer from poor scalability in big data scenarios. Various approximation methods, including random feature approximation, have been proposed to alleviate the problem. However, the statistical consistency of most of these approximate kernel methods is not well understood except for kernel ridge regression wherein it has been shown that the random feature approximation is not only computationally efficient but also statistically consistent with a minimax optimal rate of convergence. In this paper, we investigate the efficacy of random feature approximation in the context of kernel principal component analysis (KPCA) by studying the trade-off between computational and statistical behaviors of approximate KPCA. We show that the approximate KPCA is both computationally and statistically efficient compared to KPCA in terms of the error associated with reconstructing a kernel function based on its projection onto the corresponding eigenspaces. The analysis hinges on Bernstein-type inequalities for the operator and Hilbert-Schmidt norms of a self-adjoint Hilbert-Schmidt operator-valued U-statistics, which are of independent interest.

65 pages

References in corpus (1)

• On the Sample Complexity of Subspace Learning

Cited by in corpus (8)

• Random Features for Kernel Approximation: A Survey on Algorithms, Theory, and Beyond
• Kernel-based active subspaces with application to computational fluid dynamics parametric problems using the discontinuous Galerkin method
• On Kernel Derivative Approximation with Random Fourier Features
• Simple and Almost Assumption-Free Out-of-Sample Bound for Random Feature Mapping
• Optimal Rates of Sketched-regularized Algorithms for Least-Squares Regression over Hilbert Spaces
• Gain with no Pain: Efficient Kernel-PCA by Nyström Sampling
• Statistical Optimality and Computational Efficiency of Nyström Kernel PCA
• The GaussianSketch for Almost Relative Error Kernel Distance