Abstract
In the longest plane spanning tree problem, we are given a finite planar point set P, and our task is to find a plane (i.e., noncrossing) spanning tree TOPT for P with maximum total Euclidean edge length |TOPT|. Despite more than two decades of research, it remains open if this problem is NP-hard. Thus, previous efforts have focused on polynomial-time algorithms that produce plane trees whose total edge length approximates |TOPT|. The approximate trees in these algorithms all have small unweighted diameter, typically three or four. It is natural to ask whether this is a common feature of longest plane spanning trees, or an artifact of the specific approximation algorithms. We provide three results to elucidate the interplay between the approximation guarantee and the unweighted diameter of the approximate trees. First, we describe a polynomial-time algorithm to construct a plane tree TALG with diameter at most four and |TALG| = 0.546 · |TOPT|. This constitutes a substantial improvement over the state of the art. Second, we show that a longest plane tree among those with diameter at most three can be found in polynomial time. Third, for any candidate diameter d = 3, we provide upper bounds on the approximation factor that can be achieved by a longest plane tree with diameter at most d (compared to a longest plane tree without constraints). Mehr anzeigen
Persistenter Link
https://doi.org/10.3929/ethz-b-000559976Publikationsstatus
publishedExterne Links
Buchtitel
38th International Symposium on Computational GeometryZeitschrift / Serie
Leibniz International Proceedings in Informatics (LIPIcs)Band
Seiten / Artikelnummer
Verlag
Schloss Dagstuhl - Leibniz-Zentrum für InformatikKonferenz
Thema
geometric network design; spanning trees; plane straight-line graphs; approximation algorithmsOrganisationseinheit
03457 - Welzl, Emo (emeritus) / Welzl, Emo (emeritus)