Comparative study of variations in quantum approximate optimization algorithms for the Traveling Salesman Problem

The Traveling Salesman Problem (TSP) is one of the most often-used NP-Hard problems in computer science to study the effectiveness of computing models and hardware platforms. In this regard, it is also heavily used as a vehicle to study the feasibility of the quantum computing paradigm for this clas...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-07
Main Authors: Qian, Wenyang, Basili, Robert A M, Eshaghian-Wilner, Mary, Khokhar, Ashfaq, Luecke, Glenn, Vary, James P
Format: Article
Language:English
Subjects:
Algorithms
Comparative studies
Feasibility studies
Mathematical models
Optimization
Quantum computing
Qubits (quantum computing)
Simulation
Simulators
Traveling salesman problem
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The Traveling Salesman Problem (TSP) is one of the most often-used NP-Hard problems in computer science to study the effectiveness of computing models and hardware platforms. In this regard, it is also heavily used as a vehicle to study the feasibility of the quantum computing paradigm for this class of problems. In this paper, we tackle the TSP using the quantum approximate optimization algorithm (QAOA) approach by formulating it as an optimization problem. By adopting an improved qubit encoding strategy and a layerwise learning optimization protocol, we present numerical results obtained from the gate-based digital quantum simulator, specifically targeting TSP instances with 3, 4, and 5 cities. We focus on the evaluations of three distinctive QAOA mixer designs, considering their performances in terms of numerical accuracy and optimization cost. Notably, we find a well-balanced QAOA mixer design exhibits more promising potential for gate-based simulators and realistic quantum devices in the long run, an observation further supported by our noise model simulations. Furthermore, we investigate the sensitivity of the simulations to the TSP graph. Overall, our simulation results show the digital quantum simulation of problem-inspired ansatz is a successful candidate for finding optimal TSP solutions.
ISSN:2331-8422
DOI:10.48550/arxiv.2307.07243