Injectivity, stability, and positive definiteness of max filtering

12/21/2022
by   Dustin G. Mixon, et al.
0

Given a real inner product space V and a group G of linear isometries, max filtering offers a rich class of G-invariant maps. In this paper, we identify nearly sharp conditions under which these maps injectively embed the orbit space V/G into Euclidean space, and when G is finite, we estimate the map's distortion of the quotient metric. We also characterize when max filtering is a positive definite kernel.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/09/2022

Max filtering with reflection groups

Given a finite-dimensional real inner product space V and a finite subgr...
research
05/27/2022

Group-invariant max filtering

Given a real inner product space V and a group G of linear isometries, w...
research
10/27/2016

On Bochner's and Polya's Characterizations of Positive-Definite Kernels and the Respective Random Feature Maps

Positive-definite kernel functions are fundamental elements of kernel me...
research
03/31/2015

On the Projective Geometry of Kalman Filter

Convergence of the Kalman filter is best analyzed by studying the contra...
research
02/18/2013

On Translation Invariant Kernels and Screw Functions

We explore the connection between Hilbertian metrics and positive defini...
research
01/31/2012

Random Feature Maps for Dot Product Kernels

Approximating non-linear kernels using feature maps has gained a lot of ...
research
07/25/2022

3D Shape Sequence of Human Comparison and Classification using Current and Varifolds

In this paper we address the task of the comparison and the classificati...

Please sign up or login with your details

Forgot password? Click here to reset