Quantum Physics-Informed Neural Networks for Maxwell's Equations: Circuit Design, "Black Hole" Barren Plateaus Mitigation, and GPU Acceleration

• URL: http://arxiv.org/abs/2506.23246v1
• Date: Sun, 29 Jun 2025 14:10:38 GMT
• Title: Quantum Physics-Informed Neural Networks for Maxwell's Equations: Circuit Design, "Black Hole" Barren Plateaus Mitigation, and GPU Acceleration
• Authors: Ziv Chen, Gal G. Shaviner, Hemanth Chandravamsi, Shimon Pisnoy, Steven H. Frankel, Uzi Pereg,
• Abstract summary: A Quantum Physics-Informed Neural Network (QPINN) framework is proposed to solve two-dimensional (2D) time-dependent Maxwell's equations.<n>Our results demonstrate that the QPINN achieves accuracy comparable, and even greater than the classical PINN baseline.
• Score: 10.933073067185605
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Physics-Informed Neural Networks (PINNs) have emerged as a promising approach for solving partial differential equations by embedding the governing physics into the loss function associated with deep neural network. In this work, a Quantum Physics-Informed Neural Network (QPINN) framework is proposed to solve two-dimensional (2D) time-dependent Maxwell's equations. Our approach utilizes a parameterized quantum circuit in conjunction with the classical neural network architecture and enforces physical laws, including a global energy conservation principle, during training. A quantum simulation library was developed to efficiently compute circuit outputs and derivatives by leveraging GPU acceleration based on PyTorch, enabling end-to-end training of the QPINN. The method was evaluated on two 2D electromagnetic wave propagation problems: one in free space (vacuum) and one with a dielectric medium. Multiple quantum circuit ans\"atze, input scales, and an added loss term were compared in a thorough ablation study. Furthermore, recent techniques to enhance PINN convergence, including random Fourier feature embeddings and adaptive time-weighting, were incorporated. Our results demonstrate that the QPINN achieves accuracy comparable, and even greater than the classical PINN baseline, while using a significantly smaller number of trainable parameters. This study also shows that adding an energy conservation term to the loss stabilizes training and improves the physical fidelity of the solution in the lossless free-space case. This added term helps mitigate a new kind of a barren plateau (BP) related phenomenon - ``black hole'' (BH) loss landscape for the quantum experiments in that scenario. By optimizing the quantum-circuit ansatz and embedding energy-conservation constraints, our QPINN achieves up to a 19 percent higher accuracy on 2D Maxwell benchmark problems compared to a classical PINN.

Related papers

• Quantum Convolutional Neural Network with Nonlinear Effects and Barren Plateau Mitigation [0.0]
  Quantum neural networks (QNNs) leverage quantum entanglement and superposition to enable large-scale parallel linear computation.<n>However, their practical deployment is hampered by the lack of intrinsic nonlinear operations and the barren plateau phenomenon.<n>We propose a quantum neural convolutional network (QCNN) architecture that simultaneously addresses both issues.
  arXiv  Detail & Related papers  (2025-08-04T14:26:48Z)
• QCPINN: Quantum-Classical Physics-Informed Neural Networks for Solving PDEs [0.70224924046445]
  Physics-informed neural networks (PINNs) have emerged as promising methods for solving partial differential equations (PDEs)<n>We present a quantum-classical physics-informed neural network (QCPINN) that combines quantum and classical components.<n>QCPINN achieves stable convergence and comparable accuracy, while requiring approximately 10% of the trainable parameters used in classical approaches.
  arXiv  Detail & Related papers  (2025-03-20T19:52:26Z)
• Efficient charge-preserving excited state preparation with variational quantum algorithms [33.03471460050495]
  We introduce a charge-preserving VQD (CPVQD) algorithm, designed to incorporate symmetry and the corresponding conserved charge into the VQD framework. Results show applications in high-energy physics, nuclear physics, and quantum chemistry.
  arXiv  Detail & Related papers  (2024-10-18T10:30:14Z)
• Fourier Neural Operators for Learning Dynamics in Quantum Spin Systems [77.88054335119074]
  We use FNOs to model the evolution of random quantum spin systems. We apply FNOs to a compact set of Hamiltonian observables instead of the entire $2n$ quantum wavefunction.
  arXiv  Detail & Related papers  (2024-09-05T07:18:09Z)
• Training-efficient density quantum machine learning [2.918930150557355]
  We introduce density quantum neural networks, a model family that prepares mixtures of trainable unitaries.<n>This framework balances expressivity and efficient trainability, especially on quantum hardware.
  arXiv  Detail & Related papers  (2024-05-30T16:40:28Z)
• A Quantum-Classical Collaborative Training Architecture Based on Quantum State Fidelity [50.387179833629254]
  We introduce a collaborative classical-quantum architecture called co-TenQu. Co-TenQu enhances a classical deep neural network by up to 41.72% in a fair setting. It outperforms other quantum-based methods by up to 1.9 times and achieves similar accuracy while utilizing 70.59% fewer qubits.
  arXiv  Detail & Related papers  (2024-02-23T14:09:41Z)
• Quantum time dynamics mediated by the Yang-Baxter equation and artificial neural networks [3.9079297720687536]
  This study explores new strategies for mitigating quantum errors using artificial neural networks (ANN) and the Yang-Baxter equation (YBE)<n>We developed a novel method that combines ANN for noise mitigation combined with the YBE to generate noisy data.<n>This approach effectively reduces noise in quantum simulations, enhancing the accuracy of the results.
  arXiv  Detail & Related papers  (2024-01-30T15:50:06Z)
• Particle track reconstruction with noisy intermediate-scale quantum computers [0.0]
  Reconstruction of trajectories of charged particles is a key computational challenge for current and future collider experiments. The problem can be formulated as a quadratic unconstrained binary optimization (QUBO) and solved using the variational quantum eigensolver (VQE) algorithm. This work serves as a proof of principle that the VQE could be used for particle tracking and investigates modifications of the VQE to make it more suitable for optimization.
  arXiv  Detail & Related papers  (2023-03-23T13:29:20Z)
• Towards Neural Variational Monte Carlo That Scales Linearly with System Size [67.09349921751341]
  Quantum many-body problems are central to demystifying some exotic quantum phenomena, e.g., high-temperature superconductors. The combination of neural networks (NN) for representing quantum states, and the Variational Monte Carlo (VMC) algorithm, has been shown to be a promising method for solving such problems. We propose a NN architecture called Vector-Quantized Neural Quantum States (VQ-NQS) that utilizes vector-quantization techniques to leverage redundancies in the local-energy calculations of the VMC algorithm.
  arXiv  Detail & Related papers  (2022-12-21T19:00:04Z)
• QuanGCN: Noise-Adaptive Training for Robust Quantum Graph Convolutional Networks [124.7972093110732]
  We propose quantum graph convolutional networks (QuanGCN), which learns the local message passing among nodes with the sequence of crossing-gate quantum operations. To mitigate the inherent noises from modern quantum devices, we apply sparse constraint to sparsify the nodes' connections. Our QuanGCN is functionally comparable or even superior than the classical algorithms on several benchmark graph datasets.
  arXiv  Detail & Related papers  (2022-11-09T21:43:16Z)
• Accelerating the training of single-layer binary neural networks using the HHL quantum algorithm [58.720142291102135]
  We show that useful information can be extracted from the quantum-mechanical implementation of Harrow-Hassidim-Lloyd (HHL) This paper shows, however, that useful information can be extracted from the quantum-mechanical implementation of HHL, and used to reduce the complexity of finding the solution on the classical side.
  arXiv  Detail & Related papers  (2022-10-23T11:58:05Z)
• Quantum reservoir neural network implementation on coherently coupled quantum oscillators [1.7086737326992172]
  We propose an implementation for quantum reservoir that obtains a large number of densely connected neurons. We analyse a specific hardware implementation based on superconducting circuits. We obtain state-of-the-art accuracy of 99 % on benchmark tasks.
  arXiv  Detail & Related papers  (2022-09-07T15:24:51Z)
• Simulating the Mott transition on a noisy digital quantum computer via Cartan-based fast-forwarding circuits [62.73367618671969]
  Dynamical mean-field theory (DMFT) maps the local Green's function of the Hubbard model to that of the Anderson impurity model. Quantum and hybrid quantum-classical algorithms have been proposed to efficiently solve impurity models. This work presents the first computation of the Mott phase transition using noisy digital quantum hardware.
  arXiv  Detail & Related papers  (2021-12-10T17:32:15Z)
• Quantum Generative Training Using R\'enyi Divergences [0.22559617939136506]
  Quantum neural networks (QNNs) are a framework for creating quantum algorithms. A major challenge in QNN development is a concentration of measure phenomenon known as a barren plateau. We show that an unbounded loss function can circumvent the existing no-go results.
  arXiv  Detail & Related papers  (2021-06-17T14:50:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.