IEICE Technical Committee Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
Tech. Rep. Archives
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2021-05-25 09:30
Acceleration of Extreme Learning Machines by Dequantization of Quantum Singular Value Decomposition
Iori Takeda, Souichi Takahira, Kousuke Mitarai, Keisuke Fujii (Osaka Univ.)
Abstract (in Japanese) (See Japanese page) 
(in English) In 2016, the quantum recommendation system was proposed by Kerenidis and Prakash, and it was shown that the singular value decomposition of a matrix of dimension n is possible on a quantum computer with O(poly(logn)) time. Furthermore, the quantum inspired algorithm was proposed by Tang in 2018, and it was shown that with an appropriate sampling, singular value decomposition can be computed in O(poly(log n)) time on classical computers as well, which is called de-quantization. In this algorithm, the matrix, which is stored with a binary search tree structure, is sampled randomly according to the row and column L2 norms so that the matrix is compressed. Then the singular value decomposition is performed for the compressed matrix is singularly decomposed, and the singular vectors obtained are used to recover the singular vectors of the original matrix. This algorithm is based on a low-rank approximation and gives a good approximation when the rank of the matrix is small. In this pa- per, we propose an application of the quantum inspired singular value decomposition to machine learning, specifically extreme learning machine, and numerically verify the effectiveness of the low-rank approximation on standard data sets used in machine learning.
Keyword (in Japanese) (See Japanese page) 
(in English) Dequantization / Quantum Singular Value Decomposition / Machine Learning / / / / /  
Reference Info. IEICE Tech. Rep.
Paper #  
Date of Issue  
ISSN  
Download PDF

Conference Information
Committee QIT  
Conference Date 2021-05-24 - 2021-05-25 
Place (in Japanese) (See Japanese page) 
Place (in English) Online 
Topics (in Japanese) (See Japanese page) 
Topics (in English) Quantum Information 
Paper Information
Registration To QIT 
Conference Code 2021-05-QIT 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Acceleration of Extreme Learning Machines by Dequantization of Quantum Singular Value Decomposition 
Sub Title (in English)  
Keyword(1) Dequantization  
Keyword(2) Quantum Singular Value Decomposition  
Keyword(3) Machine Learning  
Keyword(4)  
Keyword(5)  
Keyword(6)  
Keyword(7)  
Keyword(8)  
1st Author's Name Iori Takeda  
1st Author's Affiliation Osaka University (Osaka Univ.)
2nd Author's Name Souichi Takahira  
2nd Author's Affiliation Osaka University (Osaka Univ.)
3rd Author's Name Kousuke Mitarai  
3rd Author's Affiliation Osaka University (Osaka Univ.)
4th Author's Name Keisuke Fujii  
4th Author's Affiliation Osaka University (Osaka Univ.)
5th Author's Name  
5th Author's Affiliation ()
6th Author's Name  
6th Author's Affiliation ()
7th Author's Name  
7th Author's Affiliation ()
8th Author's Name  
8th Author's Affiliation ()
9th Author's Name  
9th Author's Affiliation ()
10th Author's Name  
10th Author's Affiliation ()
11th Author's Name  
11th Author's Affiliation ()
12th Author's Name  
12th Author's Affiliation ()
13th Author's Name  
13th Author's Affiliation ()
14th Author's Name  
14th Author's Affiliation ()
15th Author's Name  
15th Author's Affiliation ()
16th Author's Name  
16th Author's Affiliation ()
17th Author's Name  
17th Author's Affiliation ()
18th Author's Name  
18th Author's Affiliation ()
19th Author's Name  
19th Author's Affiliation ()
20th Author's Name  
20th Author's Affiliation ()
Speaker Author-1 
Date Time 2021-05-25 09:30:00 
Presentation Time 20 minutes 
Registration for QIT 
Paper #  
Volume (vol) vol. 
Number (no)  
Page  
#Pages  
Date of Issue  


[Return to Top Page]

[Return to IEICE Web Page]


The Institute of Electronics, Information and Communication Engineers (IEICE), Japan