Quantum Robustness Verification: A Hybrid Quantum-Classical Neural Network Certification Algorithm

Nicola Franco, Tom Wollschlager, Nicholas Gao, Jeanette Miriam Lorenz, Stephan Gunnemann

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

4 Zitate (Scopus)

Abstract

In recent years, quantum computers and algorithms have made significant progress indicating the prospective importance of quantum computing (QC). Especially combinatorial optimization has gained a lot of attention as an application field for near-term quantum computers, both by using gate-based QC via the Quantum Approximate Optimization Algorithm and by quantum annealing using the Ising model. However, demonstrating an advantage over classical methods in real-world applications remains an active area of research. In this work, we investigate the robustness verification of ReLU networks, which involves solving many-variable mixed-integer programs (MIPs), as a practical application. Classically, complete verification techniques struggle with large networks as the combinatorial space grows exponentially, implying that realistic networks are difficult to be verified by classical methods. To alleviate this issue, we propose to use QC for neural network verification and introduce a hybrid quantum procedure to compute provable certificates. By applying Benders decomposition, we split the MIP into a quadratic unconstrained binary optimization and a linear program which are solved by quantum and classical computers, respectively. We further improve existing hybrid methods based on the Benders decomposition by reducing the overall number of iterations and placing a limit on the maximum number of qubits required. We show that, in a simulated environment, our certificate is sound, and provides bounds on the minimum number of qubits necessary to approximate the problem. Finally, we evaluate our method within simulations and on quantum hardware.

OriginalspracheEnglisch
TitelProceedings - 2022 IEEE International Conference on Quantum Computing and Engineering, QCE 2022
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten142-153
Seitenumfang12
ISBN (elektronisch)9781665491136
DOIs
PublikationsstatusVeröffentlicht - 2022
Veranstaltung3rd IEEE International Conference on Quantum Computing and Engineering, QCE 2022 - Broomfield, USA/Vereinigte Staaten
Dauer: 18 Sept. 202223 Sept. 2022

Publikationsreihe

NameProceedings - 2022 IEEE International Conference on Quantum Computing and Engineering, QCE 2022

Konferenz

Konferenz3rd IEEE International Conference on Quantum Computing and Engineering, QCE 2022
Land/GebietUSA/Vereinigte Staaten
OrtBroomfield
Zeitraum18/09/2223/09/22

Fingerprint

Untersuchen Sie die Forschungsthemen von „Quantum Robustness Verification: A Hybrid Quantum-Classical Neural Network Certification Algorithm“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren