Quantum transfer component analysis for domain adaptation

TL;DR

This paper introduces two quantum algorithms for transfer component analysis in domain adaptation, achieving exponential speedup over classical methods and enabling implementation on near-term quantum devices.

Contribution

It presents the first quantum implementations of TCA, including a linear-algebra-based algorithm with exponential speedup and a variational algorithm suitable for near-term quantum hardware.

Findings

Linear-algebra-based quantum TCA has complexity $O( ext{poly}(\log(n_s + n_t)))$

Quantum TCA can be exponentially faster than classical TCA

Variational quantum TCA is feasible on near-term quantum devices

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.