Abstract
We study the geometry of tropical Fermat–Weber points, that is, optimal solutions to a location problem over a projective space using a dissimilarity measure derived from the tropical metric. It is well-known that for a given sample, such points are not necessarily unique, and we show that the set of all possible Fermat–Weber points forms a polytrope. This follows from the fact that our location problem turns out to be dual to a particular minimum-cost flow problem, and we describe the polytrope of optimal locations in the terminology of tropical geometry. We also provide a simple gradient descent algorithm that converges to the Fermat–Weber polytrope.
Funding Information
  • NSF (DMS 2409819)
  • NSF (DMS-1929348)
  • Japan Society for the Promotion of Science London (JP22K19816, JP22H02364 and JP25K15283)

This publication has 23 references indexed in Scilit: