English

Quantum Support Vector Machine without Iteration

Quantum Physics 2022-06-03 v1

Abstract

Quantum algorithms can enhance machine learning in different aspects. In 2014, Rebentrost et al.et~al. constructed a least squares quantum support vector machine (LS-QSVM), in which the Swap Test plays a crucial role in realizing the classification. However, as the output states of a previous test cannot be reused for a new test in the Swap Test, the quantum algorithm LS-QSVM has to be repeated in preparing qubits, manipulating operations, and carrying out the measurement. This paper proposes a QSVM based on the generalized quantum amplitude estimation (AE-QSVM) which gets rid of the constraint of repetitive processes and saves the quantum resources. At first, AE-QSVM is trained by using the quantum singular value decomposition. Then, a query sample is classified by using the generalized quantum amplitude estimation in which high accuracy can be achieved by adding auxiliary qubits instead of repeating the algorithm. The complexity of AE-QSVM is reduced to O(κ3ε3(log(mn)+1))O(\kappa^{3}\varepsilon^{-3}(log(mn)+1)) with an accuracy ε\varepsilon, where mm is the number of training vectors, nn is the dimension of the feature space, and κ\kappa is the condition number. Experiments demonstrate that AE-QSVM is advantageous in terms of training matrix, the number of iterations, space complexity, and time complexity.

Keywords

Cite

@article{arxiv.2206.00909,
  title  = {Quantum Support Vector Machine without Iteration},
  author = {Rui Zhang and Jian Wang and Nan Jiang and Zichen Wang},
  journal= {arXiv preprint arXiv:2206.00909},
  year   = {2022}
}

Comments

10 pages,4 figures