The Spectral-Domain 𝒲_2 Wasserstein Distance for Elliptical Processes and the Spectral-Domain Gelbrich Bound

12/07/2020
by   Song Fang, et al.
0

In this short note, we introduce the spectral-domain 𝒲_2 Wasserstein distance for elliptical stochastic processes in terms of their power spectra. We also introduce the spectral-domain Gelbrich bound for processes that are not necessarily elliptical.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/12/2018

A note on reinforcement learning with Wasserstein distance regularisation, with applications to multipolicy learning

In this note we describe an application of Wasserstein distance to Reinf...
research
12/07/2022

Unsupervised spectral-band feature identification for optimal process discrimination

Changes in real-world dynamic processes are often described in terms of ...
research
11/27/2016

Kernel classification of connectomes based on earth mover's distance between graph spectra

In this paper, we tackle a problem of predicting phenotypes from structu...
research
08/25/2020

Sequences of well-distributed vertices on graphs and spectral bounds on optimal transport

Given a graph G=(V,E), suppose we are interested in selecting a sequence...
research
05/13/2021

Analysis of stochastic Lanczos quadrature for spectrum approximation

The cumulative empirical spectral measure (CESM) Φ[𝐀] : ℝ→ [0,1] of a n×...
research
02/01/2023

The Weisfeiler-Lehman Distance: Reinterpretation and Connection with GNNs

In this paper, we present a novel interpretation of the so-called Weisfe...

Please sign up or login with your details

Forgot password? Click here to reset