DeepAI AI Chat
Log In Sign Up

Comparing Distributions and Shapes using the Kernel Distance

by   Sarang Joshi, et al.

Starting with a similarity function between objects, it is possible to define a distance metric on pairs of objects, and more generally on probability distributions over them. These distance metrics have a deep basis in functional analysis, measure theory and geometric measure theory, and have a rich structure that includes an isometric embedding into a (possibly infinite dimensional) Hilbert space. They have recently been applied to numerous problems in machine learning and shape analysis. In this paper, we provide the first algorithmic analysis of these distance metrics. Our main contributions are as follows: (i) We present fast approximation algorithms for computing the kernel distance between two point sets P and Q that runs in near-linear time in the size of (P cup Q) (note that an explicit calculation would take quadratic time). (ii) We present polynomial-time algorithms for approximately minimizing the kernel distance under rigid transformation; they run in time O(n + poly(1/epsilon, log n)). (iii) We provide several general techniques for reducing complex objects to convenient sparse representations (specifically to point sets or sets of points sets) which approximately preserve the kernel distance. In particular, this allows us to reduce problems of computing the kernel distance between various types of objects such as curves, surfaces, and distributions to computing the kernel distance between point sets. These take advantage of the reproducing kernel Hilbert space and a new relation linking binary range spaces to continuous range spaces with bounded fat-shattering dimension.


page 1

page 2

page 3

page 4


Relative Error RKHS Embeddings for Gaussian Kernels

We show how to obliviously embed into the reproducing kernel Hilbert spa...

Quantum Mean Embedding of Probability Distributions

The kernel mean embedding of probability distributions is commonly used ...

Computing Functions of Random Variables via Reproducing Kernel Hilbert Space Representations

We describe a method to perform functional operations on probability dis...

Algorithms for metric learning via contrastive embeddings

We study the problem of supervised learning a metric space under discrim...

Approximating the Quadratic Transportation Metric in Near-Linear Time

Computing the quadratic transportation metric (also called the 2-Wassers...

H-Sets for Kernel-Based Spaces

The concept of H-sets as introduced by Collatz in 1956 was very useful i...

Low-Complexity Data-Parallel Earth Mover's Distance Approximations

The Earth Mover's Distance (EMD) is a state-of-the art metric for compar...