Complex matter field universal models with optimal scaling for solving combinatorial optimization problems
Statistical Mechanics
2022-01-27 v1 Disordered Systems and Neural Networks
Computational Complexity
Emerging Technologies
Quantum Physics
Abstract
We develop a universal model based on the classical complex matter fields that allow the optimal mapping of many real-life NP-hard combinatorial optimisation problems into the problem of minimising a spin Hamiltonian. We explicitly formulate one-to-one mapping for three famous problems: graph colouring, the travelling salesman, and the modular N-queens problem. We show that such a formulation allows for several orders of magnitude improvement in the search for the global minimum compared to the standard Ising formulation. At the same time, the amplitude dynamics escape from the local minima.
Cite
@article{arxiv.2201.10595,
title = {Complex matter field universal models with optimal scaling for solving combinatorial optimization problems},
author = {Natalia G. Berloff},
journal= {arXiv preprint arXiv:2201.10595},
year = {2022}
}
Comments
5 pages, 3 figures