Fourier Sparse Leverage Scores and Approximate Kernel Learning
arXiv:2006.07340
Abstract
We prove new explicit upper bounds on the leverage scores of Fourier sparse functions under both the Gaussian and Laplace measures. In particular, we study -sparse functions of the form for coefficients and frequencies . Bounding Fourier sparse leverage scores under various measures is of pure mathematical interest in approximation theory, and our work extends existing results for the uniform measure [Erd17,CP19a]. Practically, our bounds are motivated by two important applications in machine learning: 1. Kernel Approximation. They yield a new random Fourier features algorithm for approximating Gaussian and Cauchy (rational quadratic) kernel matrices. For low-dimensional data, our method uses a near optimal number of features, and its runtime is polynomial in the of the approximated kernel matrix. It is the first "oblivious sketching method" with this property for any kernel besides the polynomial kernel, resolving an open question of [AKM+17,AKK+20b]. 2. Active Learning. They can be used as non-uniform sampling distributions for robust active learning when data follows a Gaussian or Laplace distribution. Using the framework of [AKM+19], we provide essentially optimal results for bandlimited and multiband interpolation, and Gaussian process regression. These results generalize existing work that only applies to uniformly distributed data.
References in corpus (10)
- Scikit-learn: Machine Learning in Python
- Gaussian Process Kernels for Pattern Discovery and Extrapolation
- Coherence Motivated Sampling and Convergence Analysis of Least-Squares Polynomial Chaos Regression
- Recursive Sampling for the Nyström Method
- Random Fourier Features for Kernel Ridge Regression: Approximation Bounds and Statistical Guarantees
- Revisiting the Nystrom Method for Improved Large-Scale Machine Learning
- Leveraged volume sampling for linear regression
- Active Regression via Linear-Sample Sparsification
- On Sampling Random Features From Empirical Leverage Scores: Implementation and Theoretical Guarantees
- Inequalities for exponential sums