|
|
|
Quantum partial least squares regression algorithm for multiple correlation problem |
| Yan-Yan Hou(侯艳艳)1,2,3, Jian Li(李剑)1,†, Xiu-Bo Chen(陈秀波)3,4, and Yuan Tian(田源)1 |
1 School of Artificial Intelligence, Beijing University of Post and Telecommunications, Beijing 100876, China;
2 College of Information Science and Engineering, Zaozhuang University, Zaozhuang 277160, China;
3 Information Security Center, State Key Laboratory of Networking and Switching Technology, Beijing University of Post and Telecommunications, Beijing 100876, China;
4 GuiZhou University, Guizhou Provincial Key Laboratory of Public Big Data, Guiyang 550025, China |
|
|
|
|
Abstract Partial least squares (PLS) regression is an important linear regression method that efficiently addresses the multiple correlation problem by combining principal component analysis and multiple regression. In this paper, we present a quantum partial least squares (QPLS) regression algorithm. To solve the high time complexity of the PLS regression, we design a quantum eigenvector search method to speed up principal components and regression parameters construction. Meanwhile, we give a density matrix product method to avoid multiple access to quantum random access memory (QRAM) during building residual matrices. The time and space complexities of the QPLS regression are logarithmic in the independent variable dimension n, the dependent variable dimension w, and the number of variables m. This algorithm achieves exponential speed-ups over the PLS regression on n, m, and w. In addition, the QPLS regression inspires us to explore more potential quantum machine learning applications in future works.
|
Received: 27 April 2021
Revised: 04 August 2021
Accepted manuscript online: 07 August 2021
|
|
PACS:
|
03.67.Ac
|
(Quantum algorithms, protocols, and simulations)
|
| |
03.67.Lx
|
(Quantum computation architectures and implementations)
|
|
| Fund: Project supported by the Fundamental Research Funds for the Central Universities, China (Grant No. 2019XD-A02), the National Natural Science Foundation of China (Grant Nos. U1636106, 61671087, 61170272, and 92046001), Natural Science Foundation of Beijing Municipality, China (Grant No. 4182006), Technological Special Project of Guizhou Province, China (Grant No. 20183001), and the Foundation of Guizhou Provincial Key Laboratory of Public Big Data (Grant Nos. 2018BDKFJJ016 and 2018BDKFJJ018). |
Corresponding Authors:
Jian Li
E-mail: lijian@bupt.edu.cn
|
Cite this article:
Yan-Yan Hou(侯艳艳), Jian Li(李剑), Xiu-Bo Chen(陈秀波), and Yuan Tian(田源) Quantum partial least squares regression algorithm for multiple correlation problem 2022 Chin. Phys. B 31 030304
|
[1] Krzywinski M and Altman N 2015 Nature Methods 12 1103
[2] Momma M and Bennett K P 2003 Learning Theory and Kernel Machines 2777 216
[3] Li B M, Hu M L and Fan H 2019 Acta Phys. Sin. 68 030304 (in Chinese)
[4] Kong X Y, Zhu Y Y, Wen J W, Xin T, Li K R and Long G L 2018 Acta Phys. Sin. 67 220301 (in Chinese)
[5] Kerenidis I and Prakash A 2020 Phys. Rev. A 101 022316
[6] Schuld M, Fingerhuth M and Petruccione F 2017 Europhys. Lett. 119 60002
[7] Schuld M and Petruccione F 2018 Sci. Rep. 8 2772
[8] Zhao Z K, Fitzsimons J K and Fitzsimons J F 2019 Phys. Rev. A 99 052331
[9] Yu C H, Gao F and Wen Q Y 2021 IEEE Transactions on Knowledge and Data Engineering 33 858
[10] Hou Y Y, Li J, Chen X B, Li H J, Li C Y, Tian Y, Li L L, Cao Z W and Wang N 2020 Quantum Inf. Process. 19 278
[11] Song X T, Li H W, Yin Z Q, Liang W Y, Zhang C M, Han Y G, Chen W and Han Z F 2015 Chin. Phys. Lett. 32 80302
[12] Li Q, He Y and Jiang J P 2011 Quantum Inf. Process. 10 13
[13] Lloyd S, Mohseni M and Rebentrost P 2014 Nat. Phys. 10 631
[14] Chen X Y 2015 Chin. Phys. Lett. 32 10301
[15] Cao X and Shang Y 2014 Chin. Phys. Lett. 31 110302
[16] Daskin A 2016 Quantum Inf. Process. 15 4013
[17] Yu C H, Gao F, Wang Q L and Wen Q Y 2016 Phys. Rev. A 94 042311
[18] Rozema L A, Mahler D H, Hayat A, Turner P S and Steinberg A M 2014 Phys. Rev. Lett. 113 160504
[19] Yang Y X, Chiribella G and Hayashi M 2016 Phys. Rev. Lett. 117 090502
[20] Yang Y X, Chiribella G and Ebler D 2016 Phys. Rev. Lett. 116 080501
[21] Chai G, Cao Z, Liu W, Wang S, Huang P and Zeng G 2019 Phys. Rev. A 99 032326
[22] Biamonte J, Wittek W, Pancotti N, Rebentrost P, Wiebe N and Lloyd S 2017 Nature 549 195
[23] Dunjko V and Briegel H J 2018 Reports on Progress in Physics 81 074001
[24] Duan B J, Yuan J B, Liu Y and Li D 2017 Phys. Rev. A 96 032301
[25] Lu T C, Yu G R and Juang J C 2013 IEEE Transactions on Neural Networks and Learning Systems 24 1266
[26] Carleo G and Troyer M 2017 Science 355 602
[27] Rebentrost P, Bromley T R, Weedbrook C and Lloyd S 2018 Phys. Rev. A 98 042308
[28] Cong I, Choi S and Lukin M D 2019 Nat. Phys. 15 1273
[29] Sun J, Lu S F and Liu F 2014 Chin. Phys. Lett. 31 070304
[30] Harrow A W, Hassidim A and Lloyd S 2009 Phys. Rev. Lett. 103 150502
[31] Wiebe N, Braun D and Lloyd S 2012 Phys. Rev. Letter 109 050505
[32] Schuld M, Sinayskiy I and Petruccione F 2016 Phys. Rev. A 94 022342
[33] Wang G M 2012 Phys. Rev. A 96 012335
[34] Giovannetti V, Lloyd S and Maccone L 2008 Phys. Rev. Lett. 100 160501
[35] Schuld M and Petruccione F 2018 Sci. Rep. 8 2772
[36] Lloyd S, Mohseni M and Rebentrost P 2014 Nat. Phys. 10 631
[37] Yu C H, Gao F, Lin S and Wang J B 2019 Quantum Inf. Process. 18 249
[38] Yang L, Li K and Dai H Y 2019 Acta Phys. Sin. 68 140301 (in Chinese)
[39] Chen X, Zhang Z W and Zhao H 2016 Chin. Phys. Lett. 33 104203
[40] Cincio L, Subasi Y, Sornborger A T and Coles P J 2018 New J. Phys. 20 113022
[41] Sijmen D J 1993 Chemometrics and Intelligent Laboratory Systems 18 251
[42] Duan B J, Yuan J B, Xu J and Li D 2018 Phys. Rev. A 99 032311
[43] Brassard G, Hoyer P, Mosca M and Tapp A 2002 Contemporary Mathematics 305 53 |
| No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
Altmetric
|
|
blogs
Facebook pages
Wikipedia page
Google+ users
|
Online attention
Altmetric calculates a score based on the online attention an article receives. Each coloured thread in the circle represents a different type of online attention. The number in the centre is the Altmetric score. Social media and mainstream news media are the main sources that calculate the score. Reference managers such as Mendeley are also tracked but do not contribute to the score. Older articles often score higher because they have had more time to get noticed. To account for this, Altmetric has included the context data for other articles of a similar age.
View more on Altmetrics
|
|
|
