Variational Quantum AdaBoost with Supervised Learning Guarantee

• URL: http://arxiv.org/abs/2402.02376v1
• Date: Sun, 4 Feb 2024 07:18:44 GMT
• Title: Variational Quantum AdaBoost with Supervised Learning Guarantee
• Authors: Yabo Wang, Xin Wang, Bo Qi and Daoyi Dong
• Abstract summary: We show that variational quantum AdaBoost can achieve much higher accuracy in prediction, but also help mitigate the impact of noise. Our work indicates that in the current NISQ era, introducing appropriate ensemble methods is particularly valuable in improving the performance of quantum machine learning algorithms.
• Score: 8.163913266445304
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although variational quantum algorithms based on parameterized quantum circuits promise to achieve quantum advantages, in the noisy intermediate-scale quantum (NISQ) era, their capabilities are greatly constrained due to limited number of qubits and depth of quantum circuits. Therefore, we may view these variational quantum algorithms as weak learners in supervised learning. Ensemble methods are a general technique in machine learning for combining weak learners to construct a more accurate one. In this paper, we theoretically prove and numerically verify a learning guarantee for variational quantum adaptive boosting (AdaBoost). To be specific, we theoretically depict how the prediction error of variational quantum AdaBoost on binary classification decreases with the increase of the number of boosting rounds and sample size. By employing quantum convolutional neural networks, we further demonstrate that variational quantum AdaBoost can not only achieve much higher accuracy in prediction, but also help mitigate the impact of noise. Our work indicates that in the current NISQ era, introducing appropriate ensemble methods is particularly valuable in improving the performance of quantum machine learning algorithms.

Related papers

• Provably Robust Training of Quantum Circuit Classifiers Against Parameter Noise [49.97673761305336]
  Noise remains a major obstacle to achieving reliable quantum algorithms.<n>We present a provably noise-resilient training theory and algorithm to enhance the robustness of parameterized quantum circuit classifiers.
  arXiv  Detail & Related papers  (2025-05-24T02:51:34Z)
• Quantum Classifiers with Trainable Kernel [15.908830091887719]
  We devise a universally trainable quantum feature mapping layout to broaden the scope of feature states.<n>We also propose an improved quantum support vector machine that employs partially evenly weighted trial states.<n>As a promotion, we propose a quantum iterative multi-classifier framework for one-versus-one and one-versus-rest approaches.
  arXiv  Detail & Related papers  (2025-05-07T08:38:50Z)
• Quantum ensemble learning with a programmable superconducting processor [21.725285453891022]
  We introduce AdaBoost.Q, a quantum adaptation of the classical adaptive boosting (AdaBoost) algorithm. We experimentally demonstrate the versatility of our approach on a programmable superconducting processor. We achieve an accuracy above 86% for a ten-class classification task over 10,000 test samples, and an accuracy of 100% for a quantum feature recognition task over 1,564 test samples.
  arXiv  Detail & Related papers  (2025-03-14T03:30:34Z)
• Quantum machine learning for multiclass classification beyond kernel methods [21.23851138896271]
  We propose a quantum algorithm that demonstrates that quantum kernel methods enhance the efficiency of multiclass classification in real-world applications. The results from quantum simulations reveal that the quantum algorithm outperforms its classical counterpart in handling six real-world classification problems.
  arXiv  Detail & Related papers  (2024-11-05T08:58:30Z)
• Quantum Subroutine for Variance Estimation: Algorithmic Design and Applications [80.04533958880862]
  Quantum computing sets the foundation for new ways of designing algorithms. New challenges arise concerning which field quantum speedup can be achieved. Looking for the design of quantum subroutines that are more efficient than their classical counterpart poses solid pillars to new powerful quantum algorithms.
  arXiv  Detail & Related papers  (2024-02-26T09:32:07Z)
• Power Characterization of Noisy Quantum Kernels [52.47151453259434]
  We show that noise may make quantum kernel methods to only have poor prediction capability, even when the generalization error is small. We provide a crucial warning to employ noisy quantum kernel methods for quantum computation.
  arXiv  Detail & Related papers  (2024-01-31T01:02:16Z)
• 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)
• Ensemble-learning variational shallow-circuit quantum classifiers [4.104704267247209]
  We propose two ensemble-learning classification methods, namely bootstrap aggregating and adaptive boosting. The protocols have been exemplified for classical handwriting digits as well as quantum phase discrimination of a symmetry-protected topological Hamiltonian.
  arXiv  Detail & Related papers  (2023-01-30T07:26:35Z)
• Certified Robustness of Quantum Classifiers against Adversarial Examples through Quantum Noise [68.1992787416233]
  We show that adding quantum random rotation noise can improve robustness in quantum classifiers against adversarial attacks. We derive a certified robustness bound to enable quantum classifiers to defend against adversarial examples.
  arXiv  Detail & Related papers  (2022-11-02T05:17:04Z)
• Improving Quantum Classifier Performance in NISQ Computers by Voting Strategy from Ensemble Learning [9.257859576573942]
  Large error rates occur in quantum algorithms due to quantum decoherence and imprecision of quantum gates. In this study, we suggest that ensemble quantum classifiers be optimized with plurality voting.
  arXiv  Detail & Related papers  (2022-10-04T14:59:58Z)
• Recent advances for quantum classifiers [2.459525036555352]
  We will review a number of quantum classification algorithms, including quantum support vector machine, quantum kernel methods, quantum decision tree, and quantum nearest neighbor algorithm. We will then introduce the variational quantum classifiers, which are essentially variational quantum circuits for classifications.
  arXiv  Detail & Related papers  (2021-08-30T18:00:00Z)
• Towards understanding the power of quantum kernels in the NISQ era [79.8341515283403]
  We show that the advantage of quantum kernels is vanished for large size datasets, few number of measurements, and large system noise. Our work provides theoretical guidance of exploring advanced quantum kernels to attain quantum advantages on NISQ devices.
  arXiv  Detail & Related papers  (2021-03-31T02:41:36Z)
• Quantum circuit architecture search for variational quantum algorithms [88.71725630554758]
  We propose a resource and runtime efficient scheme termed quantum architecture search (QAS) QAS automatically seeks a near-optimal ansatz to balance benefits and side-effects brought by adding more noisy quantum gates. We implement QAS on both the numerical simulator and real quantum hardware, via the IBM cloud, to accomplish data classification and quantum chemistry tasks.
  arXiv  Detail & Related papers  (2020-10-20T12:06:27Z)
• Quantum Machine Learning for Particle Physics using a Variational Quantum Classifier [0.0]
  We propose a novel hybrid variational quantum classifier that combines the quantum gradient descent method with steepest gradient descent to optimise the parameters of the network. We find that this algorithm has a better learning outcome than a classical neural network or a quantum machine learning method trained with a non-quantum optimisation method.
  arXiv  Detail & Related papers  (2020-10-14T18:05:49Z)

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.