Quantum transfer component analysis for domain adaptation

Abstract

Domain adaptation, a crucial sub-field of transfer learning, aims to utilize known knowledge of one data set to accomplish tasks on another data set. In this paper, we perform one of the most representative domain adaptation algorithms, transfer component analysis (TCA), on quantum devices. Two different quantum implementations of this transfer learning algorithm; namely, the linear-algebra-based quantum TCA algorithm and the variational quantum TCA algorithm, are presented. The algorithmic complexity of the linear-algebra-based quantum TCA algorithm is $O(\mathrm{poly}(\log (n_s+n_t)))$, where $n_s$ and $n_t$ are input sample size. Compared with the corresponding classical algorithm, the linear-algebra-based quantum TCA can be performed on a universal quantum computer with exponential speedup in the number of given samples. Finally, the variational quantum TCA algorithm based on a quantum-classical hybrid procedure, that can be implemented on the near term quantum devices, is proposed.

8 pages,5 figures

References in corpus (22)

• A variational eigenvalue solver on a quantum processor
• Quantum algorithm for solving linear systems of equations
• Supervised learning with quantum enhanced feature spaces
• Quantum support vector machine for big data classification
• Quantum machine learning in feature Hilbert spaces
• Quantum principal component analysis
• Quantum fingerprinting
• Quantum random access memory
• Quantum generative adversarial learning
• Quantum algorithms for supervised and unsupervised machine learning
• Quantum Data Fitting
• Quantum generative adversarial networks
• Variational Quantum Computation of Excited States
• Transfer learning in hybrid classical-quantum neural networks
• Prediction by linear regression on a quantum computer
• The SWAP test and the Hong-Ou-Mandel effect are equivalent
• Quantum singular value decomposition of non-sparse low-rank matrices
• Quantum Discriminant Analysis for Dimensionality Reduction and Classification
• Measurement-based quantum phase estimation algorithm for finding eigenvalues of non-unitary matrices
• A Universal Quantum Circuit Scheme For Finding Complex Eigenvalues
• Short-depth circuits for efficient expectation value estimation
• Quantum algorithm for finding the negative curvature direction in non-convex optimization

Cited by in corpus (1)

• Quantum correlation alignment for unsupervised domain adaptation