WorksComputer Science
Reducing Asymmetric Path TSP to Asymmetric TSP
Abstract
In the Asymmetric Traveling Salesman Problem (Asymmetric TSP), we are given distances between vertices that satisfy the triangle inequality but need not be symmetric, and we seek a shortest tour through all vertices. In its path version, Asymmetric Path TSP, two vertices and are prescribed, and we seek a shortest path from to through all vertices. Both problems are equivalent to their versions with arbitrary nonnegative edge costs on a directed graph, in which vertices may be visited more than once. We show that for all constants and , any -approximation algorithm for Asymmetric TSP yields an -approximation algorithm for Asymmetric Path TSP. The best previous reduction of this kind, due to Feige and Singh, yields an -approximation algorithm. Our result answers an open question of Traub and Vygen. Consequently, every constant-factor approximation guarantee for Asymmetric TSP carries over to Asymmetric Path TSP up to an arbitrarily small additive error.