Year: 2026
Type: preprint
Abstract: Wang and Sitters' rounding scheme for graph balancing (each job allowed on at most two machines) keeps the makespan, the busiest machine's load, within 11/6 of the optimum, and a companion note shows that no smaller constant holds. One suspected cause is Step 3's freedom to match leftover jobs to slots in any valid way. We show that removing that freedom does not improve the constant. An idealized oracle that always picks the valid matching with the smallest makespan still has worst-case constant exactly 11/6 against the optimum. Both natural 7/4 bounds for it, against the relaxation's target and against the optimum, are false. Requiring Step 1 to return a vertex (corner) of the relaxation does not help when that vertex is chosen adversarially. The loss therefore does not come from Step 3's freedom alone. We also prove a reduction confining every overload above 7/4 to two shapes, give a seven-machine instance on which the natural two-phase repair fails, and prove a strict 7/4 bound on the generalized three-path family.
Source: arXiv (Cornell University)
Author: Shavit, Adam Y.
Institutions: The Graduate Center, CUNY, Hunter College
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Nanjing Institute of Technology
OpenAlex ID: W7212162415