Subspace Preserving Quantum Convolutional Neural Network Architectures

• URL: http://arxiv.org/abs/2409.18918v1
• Date: Fri, 27 Sep 2024 17:04:30 GMT
• Title: Subspace Preserving Quantum Convolutional Neural Network Architectures
• Authors: Léo Monbroussou, Jonas Landman, Letao Wang, Alex B. Grilo, Elham Kashefi,
• Abstract summary: Subspace preserving quantum circuits are a class of quantum algorithms that rely on some symmetries in computation. We propose a novel convolutional network model based on Hamming weight preserving quantum circuits. Our proposal offers significant running time advantages over classical deep-learning architecture.
• Score: 3.0017241250121387
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Subspace preserving quantum circuits are a class of quantum algorithms that, relying on some symmetries in the computation, can offer theoretical guarantees for their training. Those algorithms have gained extensive interest as they can offer polynomial speed-up and can be used to mimic classical machine learning algorithms. In this work, we propose a novel convolutional neural network architecture model based on Hamming weight preserving quantum circuits. In particular, we introduce convolutional layers, and measurement based pooling layers that preserve the symmetries of the quantum states while realizing non-linearity using gates that are not subspace preserving. Our proposal offers significant polynomial running time advantages over classical deep-learning architecture. We provide an open source simulation library for Hamming weight preserving quantum circuits that can simulate our techniques more efficiently with GPU-oriented libraries. Using this code, we provide examples of architectures that highlight great performances on complex image classification tasks with a limited number of qubits, and with fewer parameters than classical deep-learning architectures.

Related papers

• Efficient Learning for Linear Properties of Bounded-Gate Quantum Circuits [63.733312560668274]
  Given a quantum circuit containing d tunable RZ gates and G-d Clifford gates, can a learner perform purely classical inference to efficiently predict its linear properties? We prove that the sample complexity scaling linearly in d is necessary and sufficient to achieve a small prediction error, while the corresponding computational complexity may scale exponentially in d. We devise a kernel-based learning model capable of trading off prediction error and computational complexity, transitioning from exponential to scaling in many practical settings.
  arXiv  Detail & Related papers  (2024-08-22T08:21:28Z)
• 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)
• Learning To Optimize Quantum Neural Network Without Gradients [3.9848482919377006]
  We introduce a novel meta-optimization algorithm that trains a emphmeta-optimizer network to output parameters for the quantum circuit. We show that we achieve a better quality minima in fewer circuit evaluations than existing gradient based algorithms on different datasets.
  arXiv  Detail & Related papers  (2023-04-15T01:09:12Z)
• QNEAT: Natural Evolution of Variational Quantum Circuit Architecture [95.29334926638462]
  We focus on variational quantum circuits (VQC), which emerged as the most promising candidates for the quantum counterpart of neural networks. Although showing promising results, VQCs can be hard to train because of different issues, e.g., barren plateau, periodicity of the weights, or choice of architecture. We propose a gradient-free algorithm inspired by natural evolution to optimize both the weights and the architecture of the VQC.
  arXiv  Detail & Related papers  (2023-04-14T08:03:20Z)
• TeD-Q: a tensor network enhanced distributed hybrid quantum machine learning framework [59.07246314484875]
  TeD-Q is an open-source software framework for quantum machine learning. It seamlessly integrates classical machine learning libraries with quantum simulators. It provides a graphical mode in which the quantum circuit and the training progress can be visualized in real-time.
  arXiv  Detail & Related papers  (2023-01-13T09:35:05Z)
• Quantum compression with classically simulatable circuits [0.5735035463793007]
  We present a strategy to design quantum autoencoders using evolutionary algorithms for transforming quantum information into lower-dimensional representations. We successfully demonstrate the initial applications of the algorithm for compressing different families of quantum states. This approach opens the possibility of using classical logic to find low representations of quantum data, using fewer computational resources.
  arXiv  Detail & Related papers  (2022-07-06T20:36:10Z)
• Towards near-term quantum simulation of materials [0.47780641233738846]
  Many quantum simulation algorithms rely on a layer of unitary evolutions generated by each term in a Hamiltonian. We present a new quantum algorithm design for materials modelling where the depth of a layer is independent of the system size. We analyse the circuit costs of this approach and present a compiler that transforms density functional theory data into quantum circuit instructions.
  arXiv  Detail & Related papers  (2022-05-30T17:07:00Z)
• Feasible Architecture for Quantum Fully Convolutional Networks [4.849886707973093]
  We propose a feasible pure quantum architecture that can be operated on noisy intermediate-scale quantum devices. Our study represents the successful training of a pure quantum fully convolutional network and discusses advantages by comparing it with the hybrid solution.
  arXiv  Detail & Related papers  (2021-10-05T01:06:54Z)
• Fixed Depth Hamiltonian Simulation via Cartan Decomposition [59.20417091220753]
  We present a constructive algorithm for generating quantum circuits with time-independent depth. We highlight our algorithm for special classes of models, including Anderson localization in one dimensional transverse field XY model. In addition to providing exact circuits for a broad set of spin and fermionic models, our algorithm provides broad analytic and numerical insight into optimal Hamiltonian simulations.
  arXiv  Detail & Related papers  (2021-04-01T19:06:00Z)
• Quantum Deformed Neural Networks [83.71196337378022]
  We develop a new quantum neural network layer designed to run efficiently on a quantum computer. It can be simulated on a classical computer when restricted in the way it entangles input states.
  arXiv  Detail & Related papers  (2020-10-21T09:46:12Z)
• Realising and compressing quantum circuits with quantum reservoir computing [2.834895018689047]
  We show how a random network of quantum nodes can be used as a robust hardware for quantum computing. Our network architecture induces quantum operations by optimising only a single layer of quantum nodes. In the few-qubit regime, sequences of multiple quantum gates in quantum circuits can be compressed with a single operation.
  arXiv  Detail & Related papers  (2020-03-21T03:29:16Z)

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.