Kernel approximation on algebraic varieties

Abstract

Low-rank approximation of kernels is a fundamental mathematical problem with widespread algorithmic applications. Often the kernel is restricted to an algebraic variety, e.g., in problems involving sparse or low-rank data. We show that significantly better approximations are obtainable in this setting: the rank required to achieve a given error depends on the variety's dimension rather than the ambient dimension, which is typically much larger. This is true in both high-precision and high-dimensional regimes. Our results are presented for smooth isotropic kernels, the predominant class of kernels used in applications. Our main technical insight is to approximate smooth kernels by polynomial kernels, and leverage two key properties of polynomial kernels that hold when they are restricted to a variety. First, their ranks decrease exponentially in the variety's co-dimension. Second, their maximum values are governed by their values over a small set of points. Together, our results provide a general approach for exploiting (approximate) "algebraic structure" in datasets in order to efficiently solve large-scale data science problems.

References in corpus (12)

• Kernel Approximation on Manifolds I: Bounding the Lebesgue Constant
• Dual-Tree Fast Gauss Transforms
• Learning Algebraic Varieties from Samples
• Kernel Approximation on Manifolds II: The $L_{\infty }$-norm of the $L_2$-projector
• Algebraic Variety Models for High-Rank Matrix Completion
• Bounding the Sensitivity of Polynomial Threshold Functions
• A New Unbiased and Efficient Class of LSH-Based Samplers and Estimators for Partition Function Computation in Log-Linear Models
• Random Features for Kernel Approximation: A Survey on Algorithms, Theory, and Beyond
• Polynomial Interpolation and Approximation in C^d
• On the numerical rank of radial basis function kernels in high dimension
• Block Basis Factorization for Scalable Kernel Matrix Evaluation
• Near Input Sparsity Time Kernel Embeddings via Adaptive Sampling

Cited by in corpus (1)

• When big data actually are low-rank, or entrywise approximation of certain function-generated matrices