Classical-to-Quantum Transfer Learning Facilitates Machine Learning with Variational Quantum Circuit

• URL: http://arxiv.org/abs/2306.03741v2
• Date: Sun, 2 Jun 2024 01:55:08 GMT
• Title: Classical-to-Quantum Transfer Learning Facilitates Machine Learning with Variational Quantum Circuit
• Authors: Jun Qi, Chao-Han Huck Yang, Pin-Yu Chen, Min-Hsiu Hsieh, Hector Zenil, Jesper Tegner,
• Abstract summary: We prove that a classical-to-quantum transfer learning architecture using a Variational Quantum Circuit (VQC) improves the representation and generalization (estimation error) capabilities of the VQC model. We show that the architecture of classical-to-quantum transfer learning leverages pre-trained classical generative AI models, making it easier to find the optimal parameters for the VQC in the training stage.
• Score: 62.55763504085508
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: While Quantum Machine Learning (QML) is an exciting emerging area, the accuracy of the loss function still needs to be improved by the number of available qubits. Here, we reformulate the QML problem such that the approximation error (representation power) does not depend on the number of qubits. We prove that a classical-to-quantum transfer learning architecture using a Variational Quantum Circuit (VQC) improves the representation and generalization (estimation error) capabilities of the VQC model. We derive analytical bounds for the approximation and estimation error. We show that the architecture of classical-to-quantum transfer learning leverages pre-trained classical generative AI models, making it easier to find the optimal parameters for the VQC in the training stage. To validate our theoretical analysis, we perform experiments on single-dot and double-dot binary classification tasks for charge stability diagrams in semiconductor quantum dots, where the related empirical results support our theoretical findings. Our analytical and empirical results demonstrate the effectiveness of classical-to-quantum transfer learning architecture in realistic tasks. This sets the stage for accelerating QML applications beyond the current limits of available qubits.

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)
• On the relation between trainability and dequantization of variational quantum learning models [1.7999333451993955]
  We study the relation between trainability and dequantization of variational quantum machine learning (QML) We introduce recipes for building PQC-based QML models which are both trainable and nondequantizable. Our work however does point toward a way forward for finding more general constructions, for which finding applications may become feasible.
  arXiv  Detail & Related papers  (2024-06-11T08:59:20Z)
• Quantum-Train: Rethinking Hybrid Quantum-Classical Machine Learning in the Model Compression Perspective [7.7063925534143705]
  We introduce the Quantum-Train(QT) framework, a novel approach that integrates quantum computing with machine learning algorithms. QT achieves remarkable results by employing a quantum neural network alongside a classical mapping model.
  arXiv  Detail & Related papers  (2024-05-18T14:35:57Z)
• Bridging Classical and Quantum Machine Learning: Knowledge Transfer From Classical to Quantum Neural Networks Using Knowledge Distillation [0.0]
  This paper introduces a new method to transfer knowledge from classical to quantum neural networks using knowledge distillation. We adapt classical convolutional neural network (CNN) architectures like LeNet and AlexNet to serve as teacher networks. Quantum models achieve an average accuracy improvement of 0.80% on the MNIST dataset and 5.40% on the more complex Fashion MNIST dataset.
  arXiv  Detail & Related papers  (2023-11-23T05:06:43Z)
• Unifying (Quantum) Statistical and Parametrized (Quantum) Algorithms [65.268245109828]
  We take inspiration from Kearns' SQ oracle and Valiant's weak evaluation oracle. We introduce an extensive yet intuitive framework that yields unconditional lower bounds for learning from evaluation queries.
  arXiv  Detail & Related papers  (2023-10-26T18:23:21Z)
• 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)
• Quantum Imitation Learning [74.15588381240795]
  We propose quantum imitation learning (QIL) with a hope to utilize quantum advantage to speed up IL. We develop two QIL algorithms, quantum behavioural cloning (Q-BC) and quantum generative adversarial imitation learning (Q-GAIL) Experiment results demonstrate that both Q-BC and Q-GAIL can achieve comparable performance compared to classical counterparts.
  arXiv  Detail & Related papers  (2023-04-04T12:47:35Z)
• A didactic approach to quantum machine learning with a single qubit [68.8204255655161]
  We focus on the case of learning with a single qubit, using data re-uploading techniques. We implement the different proposed formulations in toy and real-world datasets using the qiskit quantum computing SDK.
  arXiv  Detail & Related papers  (2022-11-23T18:25:32Z)
• Subtleties in the trainability of quantum machine learning models [0.0]
  We show that gradient scaling results for Variational Quantum Algorithms can be applied to study the gradient scaling of Quantum Machine Learning models. Our results indicate that features deemed detrimental for VQA trainability can also lead to issues such as barren plateaus in QML.
  arXiv  Detail & Related papers  (2021-10-27T20:28:53Z)
• Predicting toxicity by quantum machine learning [11.696069523681178]
  We develop QML models for predicting the toxicity of 221 phenols on the basis of quantitative structure activity relationship. Results suggest that our data encoding enhanced by quantum entanglement provided more expressive power than the previous ones.
  arXiv  Detail & Related papers  (2020-08-18T02:59:40Z)

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.