Saved in:
Bibliographic Details
Main Authors: Arroyo, Ángel, Blanc, Pablo, Parviainen, Mikko
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.01642
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910628925407232
author Arroyo, Ángel
Blanc, Pablo
Parviainen, Mikko
author_facet Arroyo, Ángel
Blanc, Pablo
Parviainen, Mikko
contents We establish Krylov-Safonov type Hölder regularity theory for solutions to quite general discrete dynamic programming equations or equivalently discrete stochastic processes on random geometric graphs. Such graphs arise for example from data clouds in graph-based machine learning. The results actually hold to functions satisfying Pucci-type extremal inequalities, and thus we cover many examples including tug-of-war games on random geometric graphs. As an application we show that under suitable assumptions when the number of data points increases, the graph functions converge to a solution of a partial differential equation.
format Preprint
id arxiv_https___arxiv_org_abs_2410_01642
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Krylov-Safonov theory for Pucci-type extremal inequalities on random data clouds
Arroyo, Ángel
Blanc, Pablo
Parviainen, Mikko
Analysis of PDEs
Probability
We establish Krylov-Safonov type Hölder regularity theory for solutions to quite general discrete dynamic programming equations or equivalently discrete stochastic processes on random geometric graphs. Such graphs arise for example from data clouds in graph-based machine learning. The results actually hold to functions satisfying Pucci-type extremal inequalities, and thus we cover many examples including tug-of-war games on random geometric graphs. As an application we show that under suitable assumptions when the number of data points increases, the graph functions converge to a solution of a partial differential equation.
title Krylov-Safonov theory for Pucci-type extremal inequalities on random data clouds
topic Analysis of PDEs
Probability
url https://arxiv.org/abs/2410.01642