mlsanityData to 7 Oct 2026

Fast Summation of Radial Kernels via QMC Slicing

arXiv 2410.01316 ↗First posted 2 Oct 2024math.NA cs.LG cs.NAcited by 7

Not on the map. Why?

Abstract (arXiv)

The fast computation of large kernel sums is a challenging task, which arises as a subproblem in any kernel method. We approach the problem by slicing, which relies on random projections to one-dimensional subspaces and fast Fourier summation. We prove bounds for the slicing error and propose a quasi-Monte Carlo (QMC) approach for selecting the projections based on spherical quadrature rules. Numerical examples demonstrate that our QMC-slicing approach significantly outperforms existing methods like (QMC-)random Fourier features, orthogonal Fourier features or non-QMC slicing on standard test datasets.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 22 of its 83 references that are in the map. First posted on arXiv 2 Oct 2024.

Builds on

22 of 83 references.

References · 22

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  2. 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 498
  3. 2015On the Equivalence between Kernel Quadrature Rules and Random Feature Expansionscited by 136
  4. 2019Maximum Mean Discrepancy Gradient Flowcited by 123
  5. 2020Kernel Operations on the GPU, with Autodiff, without Memory Overflowscited by 101
  6. 2016Orthogonal Random Featurescited by 89
  7. 2015On the Error of Random Fourier Featurescited by 76
  8. 2014Quasi-Monte Carlo Feature Maps for Shift-Invariant Kernelscited by 41
  9. 2023Generative Sliced MMD Flows with Riesz Kernelscited by 36
  10. 2018Quadrature-based features for kernel approximationcited by 25
  11. 2023Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernelcited by 25
  12. 2021Generalization Bounds for Sparse Random Feature Expansionscited by 22
10 more
  1. 2023Quasi-Monte Carlo for 3D Sliced Wassersteincited by 22
  2. 2024Deep MMD Gradient Flow without adversarial trainingcited by 18
  3. 2024(De)-regularized Maximum Mean Discrepancy Gradient Flowcited by 14
  4. 2014ASKIT: Approximate Skeletonization Kernel-Independent Treecode in High Dimensionscited by 12
  5. 2023Momentum Particle Maximum Likelihoodcited by 12
  6. 2021cuFINUFFT: a load-balanced GPU library for general-purpose nonuniform FFTscited by 11
  7. 2021The Fast Kernel Transformcited by 8
  8. 2024Fast Kernel Summation in High Dimensions via Slicing and Fourier Transformscited by 7
  9. 2016Fast spatial Gaussian process maximum likelihood estimation via skeletonization factorizationscited by 6
  10. 2024On the design of scalable, high-precision spherical-radial Fourier featurescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 1.

7 papers.

  1. 2025A Novel Sliced Fused Gromov-Wasserstein Distancecited by 9
  2. 2025Slicing the Gaussian Mixture Wasserstein Distancecited by 7
  3. 2025Slicing Wasserstein Over Wasserstein Via Functional Optimal Transportcited by 5
  4. 2024Generative Feature Training of Thin 2-Layer Networkscited by 2
  5. 2025Smoothed Distance Kernels for MMDs and Applications in Wasserstein Gradient Flowscited by 2
  6. 2025Randomized Quasi-Monte Carlo Features for Kernel Approximationcited by 0
  7. 2026Quasi Linear Kernel Attention with Infinite Capacitycited by 0