Large data limit for a phase transition model with the p-Laplacian on point clouds
Analysis of PDEs
2018-09-25 v2
Abstract
The consistency of a nonlocal anisotropic Ginzburg-Landau type functional for data classification and clustering is studied. The Ginzburg-Landau objective functional combines a double well potential, that favours indicator valued function, and the -Laplacian, that enforces regularity. Under appropriate scaling between the two terms minimisers exhibit a phase transition on the order of where is the number of data points. We study the large data asymptotics, i.e. as , in the regime where . The mathematical tool used to address this question is -convergence. In particular, it is proved that the discrete model converges to a weighted anisotropic perimeter.
Cite
@article{arxiv.1802.08703,
title = {Large data limit for a phase transition model with the p-Laplacian on point clouds},
author = {Riccardo Cristoferi and Matthew Thorpe},
journal= {arXiv preprint arXiv:1802.08703},
year = {2018}
}