Fast Statistical Leverage Score Approximation in Kernel Ridge Regression
This work addresses a computational bottleneck for researchers and practitioners using kernel methods in machine learning, offering an incremental improvement over prior techniques.
The paper tackles the high computational cost of estimating statistical leverage scores in Nyström approximation for kernel ridge regression by proposing a linear-time algorithm with theoretical guarantees, achieving orders of magnitude greater efficiency while maintaining the same prediction accuracy as existing methods.
Nyström approximation is a fast randomized method that rapidly solves kernel ridge regression (KRR) problems through sub-sampling the n-by-n empirical kernel matrix appearing in the objective function. However, the performance of such a sub-sampling method heavily relies on correctly estimating the statistical leverage scores for forming the sampling distribution, which can be as costly as solving the original KRR. In this work, we propose a linear time (modulo poly-log terms) algorithm to accurately approximate the statistical leverage scores in the stationary-kernel-based KRR with theoretical guarantees. Particularly, by analyzing the first-order condition of the KRR objective, we derive an analytic formula, which depends on both the input distribution and the spectral density of stationary kernels, for capturing the non-uniformity of the statistical leverage scores. Numerical experiments demonstrate that with the same prediction accuracy our method is orders of magnitude more efficient than existing methods in selecting the representative sub-samples in the Nyström approximation.