Improved Coresets for Kernel Density Estimates

by   Jeff M. Phillips, et al.

We study the construction of coresets for kernel density estimates. That is we show how to approximate the kernel density estimate described by a large point set with another kernel density estimate with a much smaller point set. For characteristic kernels (including Gaussian and Laplace kernels), our approximation preserves the L_∞ error between kernel density estimates within error ϵ, with coreset size 2/ϵ^2, but no other aspects of the data, including the dimension, the diameter of the point set, or the bandwidth of the kernel common to other approximations. When the dimension is unrestricted, we show this bound is tight for these kernels as well as a much broader set. This work provides a careful analysis of the iterative Frank-Wolfe algorithm adapted to this context, an algorithm called kernel herding. This analysis unites a broad line of work that spans statistics, machine learning, and geometry. When the dimension d is constant, we demonstrate much tighter bounds on the size of the coreset specifically for Gaussian kernels, showing that it is bounded by the size of the coreset for axis-aligned rectangles. Currently the best known constructive bound is O(1/ϵ^d 1/ϵ), and non-constructively, this can be improved by √(1/ϵ). This improves the best constant dimension bounds polynomially for d ≥ 3.


page 1

page 2

page 3

page 4


Near-Optimal Coresets of Kernel Density Estimates

We construct near-optimal coresets for kernel density estimate for point...

New Nearly-Optimal Coreset for Kernel Density Estimation

Given a point set P⊂ℝ^d, kernel density estimation for Gaussian kernel i...

Stochastic geometry to generalize the Mondrian Process

The Mondrian process is a stochastic process that produces a recursive p...

Kernel Estimates as General Concept for the Measuring of Pedestrian Density

The standard density definition produces scattered values. Hence approac...

Provably Efficient Kernelized Q-Learning

We propose and analyze a kernelized version of Q-learning. Although a ke...

Distribution-Sensitive Bounds on Relative Approximations of Geometric Ranges

A family R of ranges and a set X of points together define a range space...

Dimensionality Reduction for General KDE Mode Finding

Finding the mode of a high dimensional probability distribution D is a f...

Please sign up or login with your details

Forgot password? Click here to reset