TY - GEN
T1 - NRQNN
T2 - 20th International Conference on Grid, Cloud, and Cluster Computing, GCC 2024, 3rd International Conference on Quantum Technologies, ICEQT 2024, and 21st International Conference on Modeling, Simulation and Visualization Methods, MSV 2024, held as part of the World Congress in Computer Science, Computer Engineering and Applied Computing, CSCE 2024
AU - Kashif, Muhammad
AU - Shafique, Muhammad
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
PY - 2025
Y1 - 2025
N2 - This paper explores the complexities associated with training Quantum Neural Networks (QNNs) under noisy conditions, a critical consideration for Noisy Intermediate-Scale Quantum (NISQ) devices. We first demonstrate that Barren Plateaus (BPs), characterized by exponentially vanishing gradients, emerge more readily in noisy quantum environments than in ideal conditions. We then propose that careful selection of qubit measurement observable can make QNNs resilient against noise. To this end, we explore the effectiveness of various qubit measurement observables, including PauliX, PauliY, PauliZ, and a custom-designed Hermitian observable, against three types of quantum noise: Phase Damping, Phase Flip, and Amplitude Damping. Our findings reveal that QNNs employing Pauli observables are prone to an earlier emergence of BPs, notably in noisy environments, even with a smaller qubit count of four qubits. Conversely, the custom-designed Hermitian measurement observable exhibits significant resilience against all types of quantum noise, facilitating consistent trainability for QNNs up to 10 qubits. This study highlights the crucial role of observable selection and quantum noise consideration in enhancing QNN training, offering a strategic approach to improve QNN performance in the NISQ era.
AB - This paper explores the complexities associated with training Quantum Neural Networks (QNNs) under noisy conditions, a critical consideration for Noisy Intermediate-Scale Quantum (NISQ) devices. We first demonstrate that Barren Plateaus (BPs), characterized by exponentially vanishing gradients, emerge more readily in noisy quantum environments than in ideal conditions. We then propose that careful selection of qubit measurement observable can make QNNs resilient against noise. To this end, we explore the effectiveness of various qubit measurement observables, including PauliX, PauliY, PauliZ, and a custom-designed Hermitian observable, against three types of quantum noise: Phase Damping, Phase Flip, and Amplitude Damping. Our findings reveal that QNNs employing Pauli observables are prone to an earlier emergence of BPs, notably in noisy environments, even with a smaller qubit count of four qubits. Conversely, the custom-designed Hermitian measurement observable exhibits significant resilience against all types of quantum noise, facilitating consistent trainability for QNNs up to 10 qubits. This study highlights the crucial role of observable selection and quantum noise consideration in enhancing QNN training, offering a strategic approach to improve QNN performance in the NISQ era.
UR - http://www.scopus.com/inward/record.url?scp=105002363909&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=105002363909&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-85884-0_10
DO - 10.1007/978-3-031-85884-0_10
M3 - Conference contribution
AN - SCOPUS:105002363909
SN - 9783031858833
T3 - Communications in Computer and Information Science
SP - 116
EP - 131
BT - Grid, Cloud, and Cluster Computing; Quantum Technologies; and Modeling, Simulation and Visualization Methods - 20th International Conference, GCC 2024, 3rd International Conference, ICEQT 2024, and 21st International Conference, MSV 2024, Held as Part of the World Congress in Computer Science, Computer Engineering and Applied Computing, CSCE 2024, Revised Selected Papers
A2 - Arabnia, Hamid R.
A2 - Takata, Masami
A2 - Deligiannidis, Leonidas
A2 - Rivas, Pablo
A2 - Ohue, Masahito
A2 - Yasuo, Nobuaki
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 22 July 2024 through 25 July 2024
ER -