Abstract
In this paper, we propose a quantum algorithm to efficiently perform locality preserving projection (LPP) for dimensionality reduction, named quantum locality preserving projection (QLPP). We present QLPP in 4 steps and give their corresponding quantum circuits. Furthermore, we give an improved algorithm to construct the density matrix proportional to the Hermitian/non-Hermitian chain product composed of multiple Hermitian/non-Hermitian matrices in QLPP. The analysis results show that the computation complexity of QLLP is \(O(d\kappa _\mathrm{eff}^{10}\sqrt{m}\mathrm{polylog}(m)/\varepsilon ^{7})\) for \(m\gg n\), where \(\kappa _\mathrm{eff}\) is a predefined condition number, m is the number of training data with dimension n, d is the dimension of reduced dimension feature space, and \(\varepsilon \) denotes the tolerance error. It is polynomial speedup in m compared to classical LPP algorithm, whose complexity is \(O (m^2n)\).
Similar content being viewed by others
Data availability
The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.
References
Chalumuri, A., Kune, R., Manoj, B.S.: A hybrid classical-quantum approach for multi-class classification. Quantum Inf. Process. 20(3), 1–19 (2021)
Wang, Shengbin, Wang, Zhimin, Li, Wendong, Fan, Lixin, Wei, Zhiqiang, Yongjian, Gu.: Quantum fast poisson solver: the algorithm and complete and modular circuit design. Quantum Inf. Process. 19(6), 1–25 (2020)
Zhang, AnQi., Wang, XueMei, Zhao, ShengMei: The multiplier based on quantum fourier transform. CCF Trans. High Perform. Comput. 2(3), 221–227 (2020)
Hou, Yanyan, Li, Jian, Chen, Xiubo, Li, Hengji, Li, Chaoyang, Tian, Yuan, Li, Leilei, Cao, Zhengwen, Wang, Na.: Quantum algorithm for help-training semi-supervised support vector machine. Quantum Inf. Process. 19(9), 1–20 (2020)
Zhang, Yanbing, Song, Tingting, Zhihao, Wu.: An improved quantum algorithm for support matrix machines. Quantum Inf. Process. 20(7), 1–12 (2021)
Dang, Yijie, Jiang, Nan, Hao, Hu., Ji, Zhuoxiao, Zhang, Wenyin: Image classification based on quantum k-nearest-neighbor algorithm. Quantum Inf. Process. 17(9), 1–18 (2018)
Meng, Fan-Xu., Xu-Tao, Yu., Zhang, Zai-Chen.: Improved quantum algorithm for mmse-based massive mimo uplink detection. Quantum Inf. Process. 19(8), 1–17 (2020)
Ji, Yahui, Meng, Fanxu, Jin, Jiejun, Xutao, Yu., Zhang, Zaichen, You, Xiaohu, Zhang, Chuan: Quantum version of mmse-based massive mimo uplink detection. Quantum Inf. Process. 19(2), 1–28 (2020)
Chao-Hua, Yu., Gao, Fei, Wen, Qiao-Yan.: An improved quantum algorithm for ridge regression. IEEE Trans. Knowl. Data Eng. 33(3), 858–866 (2021)
Shao, Changpeng, Xiang, Hua: Quantum regularized least squares solver with parameter estimate. Quantum Inf. Process. 19(4), 1–20 (2020)
Chao-Hua, Yu., Gao, Fei, Chenghuan Liu, Du., Huynh, Mark Reynolds, Wang, Jingbo: Quantum algorithm for visual tracking. Phys. Rev. A 99(10), 022301 (2019)
Chao-Hua, Yu., Gao, Fei, Lin, Song, Wang, Jingbo: Quantum data compression by principal component analysis. Quantum Inf. Process. 18(8), 1–20 (2019)
Lloyd, Seth, Mohseni, Masoud, Rebentrost, Patrick: Quantum principal component analysis. Nat. Phys. 10(9), 631–633 (2014)
Lin, Jie, Bao, Wan-Su., Zhang, Shuo, Li, Tan, Wang, Xiang: An improved quantum principal component analysis algorithm based on the quantum singular threshold method. Phys. Lett. A 383(24), 2862–2868 (2019)
Cong, Iris, Duan, Luming: Quantum discriminant analysis for dimensionality reduction and classification. New J. Phys. 18(7), 073011 (2016)
Harrow, Aram W., Hassidim, Avinatan, Lloyd, Seth: Quantum algorithm for linear systems of equations. Phys. Rev. Lett. 103, 150502 (2009)
Duan, Bojia, Yuan, Jiabin, Juan, Xu., Li, Dan: Quantum algorithm and quantum circuit for a-optimal projection: dimensionality reduction. Phys. Rev. A 99(9), 032311 (2019)
Pan, Shi-Jie., Wan, Lin-Chun., Liu, Hai-Ling., Wang, Qing-Le., Qin, Su-Juan., Wen, Qiao-Yan., Gao, Fei: Improved quantum algorithm for a-optimal projection. Phys. Rev. A 102, 052402 (2020)
He, Xi., Sun, Li., Lyu, Chufan, Wang, Xiaoting: Quantum locally linear embedding for nonlinear dimensionality reduction. Quantum Inf. Process. 19(9), 1–21 (2020)
He, Xiaofei., Niyogi,Partha.: Locality preserving projections. In Advances in neural information processing systems, pages 153–160, 2004
Xiangjie, Hu., Sun, Yanfeng, Gao, Junbin, Yongli, Hu., Yin, Baocai: Locality preserving projection based on f-norm. In Proceedings of the AAAI Conference on Artificial Intelligence 32, 153–160 (2018)
Xiuxiu, Xu., Liang, Jiuzhen, Lv, Sisi, Qin, Wu.: Human facial expression analysis based on image granule lpp. Int. J. Mach. Learn. Cybern. 5(6), 907–921 (2014)
Zhang, Wei, Kang, Peipei, Fang, Xiaozhao, Teng, Luyao, Han, Na.: Joint sparse representation and locality preserving projection for feature extraction. Int. J. Mach. Learn. Cybern. 10(7), 1731–1745 (2019)
Shao, Yu.: Supervised global-locality preserving projection for plant leaf recognition. Comput. Electron. Agri. 158, 102–108 (2019)
Wossnig, Leonard, Zhao, Zhikuan, Prakash, Anupam: Quantum linear system algorithm for dense matrices. Phys. Rev. Lett. 120(5), 050502 (2018)
Mitarai, Kosuke, Kitagawa, Masahiro, Fujii, Keisuke: Quantum analog-digital conversion. Phys. Rev. A 99(8), 012301 (2019)
Acknowledgements
We used the part source codes of classical LPP in our numerical simulation, and we are grateful for the authors providing the open-source codes at ’Matlab codes for dimensionality reduction (subspace learning).’ This work is supported by the National Natural Science Foundation of China (61871234) and Postgraduate Research & Practice Innovation Program of Jiangsu Province (Grant KYCX19_0900, KYCX20_0816).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix A: proof of theorem
Appendix A: proof of theorem
First, we extend matrices \(\mathbf{B} _{1}, \mathbf{B} _{2},...\mathbf{B} _{k},\) to matrices \(\mathbf{B} _{1}', \mathbf{B} _{2}',...\mathbf{B} _{k}',\). The expanded matrices are shown below,
where \(j=1,2,...k\), \(r_{j}\) represents the number of rows of matrix \(\mathbf{B} _{j}\), \(2^{q-1}r_{k}\ge \max (r_{0}, r_{1}, ..., r_{k})\), q is a positive integer and \(r_0=r_1\).
Then, we extend matrices \(\mathbf{B} _{1}', \mathbf{B} _{2}',...\mathbf{B} _{k}'\) to matrices \(\mathbf{B} _{1}'', \mathbf{B} _{2}'',...\mathbf{B} _{k}''\). The expanded matrices are shown as follows.
where \(j=1, 2 ,...[\frac{k+1}{2} ]\), \([\frac{k+1}{2} ]\) is the largest integer less than \(\frac{k+1}{2}\) and \(2j+1\le k\).
When k is even, we have
otherwise
where B denotes \(\left[ \mathbf{B} _{k}... \mathbf{B} _{2}(\mathbf{B} _{1})^{\frac{1}{2}}\right] \left[ \mathbf{B} _{k}... \mathbf{B} _{2}(\mathbf{B} _{1})^{\frac{1}{2}}\right] ^{\dagger }\).
Since \(\mathbf{B} _{1}'', \mathbf{B} _{2}'',...\mathbf{B} _{k}''\) are Hermitian matrices, we can obtain the density matrix proportional to \(\mathbf{B} '\) by using the improved algorithm. Specifically, we use \(\mathbf{A} _{1}=\mathbf{B} _{1}''\), \(f_{1}(\mathbf{A} _{1})= \mathbf{A} _{1}^{\frac{1}{2} }\) and \(\mathbf{A} _{j}=\mathbf{B} _{j}''\), \(f_{j}(\mathbf{A} _{j})= \mathbf{A} _{j}\) for \(j=2, 3,..k\). When k is odd, the density matrix \({\varvec{\rho }}_\mathbf{B '} \) proportional to \(\mathbf{B} '\) is
otherwise
where \(\frac{1}{T}\) is a constant for normalization.
Removing \((\left| 1 \right\rangle \left\langle 1\right| )^{\otimes q}\) from Eq. (61) or removing \((\left| 0 \right\rangle \left\langle 0\right| )^{\otimes q}\) from Eq. (62), one can obtain the density matrix proportional to \(\left[ \mathbf{B} _{k}... \mathbf{B} _{2}{} \mathbf{B} _{1}\right] \left[ \mathbf{B} _{k}... \mathbf{B} _{2}{} \mathbf{B} _{1}\right] ^{\dagger }\).
Rights and permissions
About this article
Cite this article
He, X., Zhang, A. & Zhao, S. Quantum locality preserving projection algorithm. Quantum Inf Process 21, 86 (2022). https://doi.org/10.1007/s11128-022-03424-w
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11128-022-03424-w