• Home
  • News
  • Technology
  • Research
  • Teaching
  • Business
  • Jobs
  • Home
  • News
  • Technology
  • Research
  • Teaching
  • Business
  • Jobs
Contact
  • de
  • en

  • Home
  • News
  • Technology
  • Research
  • Teaching
  • Business
  • Jobs
Contact
  • de
  • en

Insights on Training Neural Networks for QUBO Tasks

Insights on Training Neural Networks for QUBO Tasks

T. Gabor, S. Feld, H. Safi, T. Phan, and C. Linnhoff-Popien

Abstract

Current hardware limitations restrict the potential when solving quadratic unconstrained binary optimization (QUBO) problems via the quantum approximate optimization algorithm (QAOA) or quantum annealing (QA). Thus, we consider training neural networks in this context. We first discuss QUBO problems that originate from translated instances of the traveling salesman problem (TSP): Analyzing this representation via autoencoders shows that there is way more information included than necessary to solve the original TSP. Then we show that neural networks can be used to solve TSP instances from both QUBO input and autoencoders’ hiddenstate representation. We finally generalize the approach and successfully train neural networks to solve arbitrary QUBO problems, sketching means to use neuromorphic hardware as a simulator or an additional co-processor for quantum computing.

1st International Workshop on Quantum Software Engineering (QSE at ICSE)

PDF Download


QAR-Lab – Quantum Applications and Research Laboratory
Ludwig-Maximilians-Universität München
Oettingenstraße 67
80538 Munich
Phone: +49 89 2180-9153
E-mail: qar-lab@mobile.ifi.lmu.de

© Copyright 2021

General

Team
Contact
Legal notice

Social Media

Twitter
Linkedin
Github

Language

  • de
  • en