Phase Transition in the Family of P-Resistances
Abstract
We study the family of p-resistances on graphs for p ≥ 1. This family generalizes the standard resistance distance. We prove that for any fixed graph, for p=1, the p-resistance coincides with the shortest path distance, for p=2 it coincides with the standard resistance distance, and for p → ∞ it converges to the inverse of the minimal s-t-cut in the graph. Secondly, we consider the special case of random geometric graphs (such as k-nearest neighbor graphs) when the number n of vertices in the graph tends to infinity. We prove that an interesting phase-transition takes place. There exist two critical thresholds p^* and p^** such that if p < p^*, then the p-resistance depends on meaningful global properties of the graph, whereas if p > p^**, it only depends on trivial local quantities and does not convey any useful information. We can explicitly compute the critical values: p^* = 1 + 1/(d-1) and p^** = 1 + 1/(d-2) where d is the dimension of the underlying space (we believe that the fact that there is a small gap between p^* and p^** is an artifact of our proofs. We also relate our findings to Laplacian regularization and suggest to use q-Laplacians as regularizers, where q satisfies 1/p^* + 1/q = 1.
Cite
Text
Alamgir and Luxburg. "Phase Transition in the Family of P-Resistances." Neural Information Processing Systems, 2011.Markdown
[Alamgir and Luxburg. "Phase Transition in the Family of P-Resistances." Neural Information Processing Systems, 2011.](https://mlanthology.org/neurips/2011/alamgir2011neurips-phase/)BibTeX
@inproceedings{alamgir2011neurips-phase,
title = {{Phase Transition in the Family of P-Resistances}},
author = {Alamgir, Morteza and Luxburg, Ulrike V.},
booktitle = {Neural Information Processing Systems},
year = {2011},
pages = {379-387},
url = {https://mlanthology.org/neurips/2011/alamgir2011neurips-phase/}
}