DeepAI AI Chat
Log In Sign Up

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

by   Louis Brown, et al.

Given a graph G=(V,E), suppose we are interested in selecting a sequence of vertices (x_j)_j=1^n such that {x_1, …, x_k} is `well-distributed' uniformly in k. We describe a greedy algorithm motivated by potential theory and corresponding developments in the continuous setting. The algorithm performs nicely on graphs and may be of use for sampling problems. We can interpret the algorithm as trying to greedily minimize a negative Sobolev norm; we explain why this is related to Wasserstein distance by establishing a purely spectral bound on the Wasserstein distance on graphs that mirrors R. Peyré's estimate in the continuous setting. We illustrate this with many examples and discuss several open problems.


page 1

page 2

page 3

page 4


Optimal transport and Wasserstein distances for causal models

In this paper we introduce a variant of optimal transport adapted to the...

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

In this short note, we introduce the spectral-domain 𝒲_2 Wasserstein dis...

A gradual, semi-discrete approach to generative network training via explicit wasserstein minimization

This paper provides a simple procedure to fit generative networks to tar...

A Regularized Wasserstein Framework for Graph Kernels

We propose a learning framework for graph kernels, which is theoreticall...

On the Wasserstein Distance between Classical Sequences and the Lebesgue Measure

We discuss the classical problem of measuring the regularity of distribu...

Nonlocal-interaction equation on graphs: gradient flow structure and continuum limit

We consider dynamics driven by interaction energies on graphs. We introd...