Nonnegative/Binary matrix factorization with a D-Wave quantum annealer
Abstract
D-Wave quantum annealers represent a novel computational architecture and have attracted significant interest. Much of this interest has focused on the quantum behavior of D-Wave machines, and there have been few practical algorithms that use the D-Wave. Machine learning has been identified as an area where quantum annealing may be useful. Here, we show that the D-Wave 2X can be effectively used as part of an unsupervised machine learning method. This method takes a matrix as input and produces two low-rank matrices as output—one containing latent features in the data and another matrix describing how the features can be combined to approximately reproduce the input matrix. Despite the limited number of bits in the D-Wave hardware, this method is capable of handling a large input matrix. The D-Wave only limits the rank of the two output matrices. We apply this method to learn the features from a set of facial images and compare the performance of the D-Wave to two classical tools. This method is able to learn facial features and accurately reproduce the set of facial images. The performance of the D-Wave shows some promise, but has some limitations. It outperforms the two classical codes in a benchmark whenmore »
- Authors:
- Publication Date:
- Research Org.:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Org.:
- USDOE Laboratory Directed Research and Development (LDRD) Program
- OSTI Identifier:
- 1485190
- Alternate Identifier(s):
- OSTI ID: 1489946
- Report Number(s):
- LA-UR-17-22557
Journal ID: ISSN 1932-6203; 10.1371/journal.pone.0206653
- Grant/Contract Number:
- 89233218CNA000001
- Resource Type:
- Published Article
- Journal Name:
- PLoS ONE
- Additional Journal Information:
- Journal Name: PLoS ONE Journal Volume: 13 Journal Issue: 12; Journal ID: ISSN 1932-6203
- Publisher:
- Public Library of Science (PLoS)
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; Computer Science; Mathematics
Citation Formats
O’Malley, Daniel, Vesselinov, Velimir V., Alexandrov, Boian S., Alexandrov, Ludmil B., and Olier, ed., Ivan. Nonnegative/Binary matrix factorization with a D-Wave quantum annealer. United States: N. p., 2018.
Web. doi:10.1371/journal.pone.0206653.
O’Malley, Daniel, Vesselinov, Velimir V., Alexandrov, Boian S., Alexandrov, Ludmil B., & Olier, ed., Ivan. Nonnegative/Binary matrix factorization with a D-Wave quantum annealer. United States. https://doi.org/10.1371/journal.pone.0206653
O’Malley, Daniel, Vesselinov, Velimir V., Alexandrov, Boian S., Alexandrov, Ludmil B., and Olier, ed., Ivan. Mon .
"Nonnegative/Binary matrix factorization with a D-Wave quantum annealer". United States. https://doi.org/10.1371/journal.pone.0206653.
@article{osti_1485190,
title = {Nonnegative/Binary matrix factorization with a D-Wave quantum annealer},
author = {O’Malley, Daniel and Vesselinov, Velimir V. and Alexandrov, Boian S. and Alexandrov, Ludmil B. and Olier, ed., Ivan},
abstractNote = {D-Wave quantum annealers represent a novel computational architecture and have attracted significant interest. Much of this interest has focused on the quantum behavior of D-Wave machines, and there have been few practical algorithms that use the D-Wave. Machine learning has been identified as an area where quantum annealing may be useful. Here, we show that the D-Wave 2X can be effectively used as part of an unsupervised machine learning method. This method takes a matrix as input and produces two low-rank matrices as output—one containing latent features in the data and another matrix describing how the features can be combined to approximately reproduce the input matrix. Despite the limited number of bits in the D-Wave hardware, this method is capable of handling a large input matrix. The D-Wave only limits the rank of the two output matrices. We apply this method to learn the features from a set of facial images and compare the performance of the D-Wave to two classical tools. This method is able to learn facial features and accurately reproduce the set of facial images. The performance of the D-Wave shows some promise, but has some limitations. It outperforms the two classical codes in a benchmark when only a short amount of computational time is allowed (200-20,000 microseconds), but these results suggest heuristics that would likely outperform the D-Wave in this benchmark.},
doi = {10.1371/journal.pone.0206653},
journal = {PLoS ONE},
number = 12,
volume = 13,
place = {United States},
year = {Mon Dec 10 00:00:00 EST 2018},
month = {Mon Dec 10 00:00:00 EST 2018}
}
https://doi.org/10.1371/journal.pone.0206653
Web of Science
Figures / Tables:
Works referenced in this record:
Unsupervised feature selection by regularized self-representation
journal, February 2015
- Zhu, Pengfei; Zuo, Wangmeng; Zhang, Lei
- Pattern Recognition, Vol. 48, Issue 2
GPU Computing
journal, May 2008
- Owens, J. D.; Houston, M.; Luebke, D.
- Proceedings of the IEEE, Vol. 96, Issue 5
Combining neighborhood separable subspaces for classification via sparsity regularized optimization
journal, November 2016
- Zhu, Pengfei; Hu, Qinghua; Han, Yahong
- Information Sciences, Vol. 370-371
Non-convex regularized self-representation for unsupervised feature selection
journal, April 2017
- Zhu, Pengfei; Zhu, Wencheng; Wang, Weizhi
- Image and Vision Computing, Vol. 60
The pitfalls of planar spin-glass benchmarks: raising the bar for quantum annealers (again)
journal, July 2017
- Mandrà, Salvatore; Katzgraber, Helmut G.; Thomas, Creighton
- Quantum Science and Technology, Vol. 2, Issue 3
Face recognition using eigenfaces
conference, January 1991
- Turk, M. A.; Pentland, A. P.
- Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
CPU DB: recording microprocessor history
journal, April 2012
- Danowitz, Andrew; Kelley, Kyle; Mao, James
- Communications of the ACM, Vol. 55, Issue 4
Quantum annealing with manufactured spins
journal, May 2011
- Johnson, M. W.; Amin, M. H. S.; Gildert, S.
- Nature, Vol. 473, Issue 7346
Quantum adiabatic machine learning
journal, November 2012
- Pudenz, Kristen L.; Lidar, Daniel A.
- Quantum Information Processing, Vol. 12, Issue 5
Subspace clustering guided unsupervised feature selection
journal, June 2017
- Zhu, Pengfei; Zhu, Wencheng; Hu, Qinghua
- Pattern Recognition, Vol. 66
Multi-label feature selection with missing labels
journal, February 2018
- Zhu, Pengfei; Xu, Qian; Hu, Qinghua
- Pattern Recognition, Vol. 74
Optimised simulated annealing for Ising spin glasses
journal, July 2015
- Isakov, S. V.; Zintchenko, I. N.; Rønnow, T. F.
- Computer Physics Communications, Vol. 192
Projected Gradient Methods for Nonnegative Matrix Factorization
journal, October 2007
- Lin, Chih-Jen
- Neural Computation, Vol. 19, Issue 10
What is the Computational Value of Finite-Range Tunneling?
journal, August 2016
- Denchev, Vasil S.; Boixo, Sergio; Isakov, Sergei V.
- Physical Review X, Vol. 6, Issue 3
Minor-embedding in adiabatic quantum computation: II. Minor-universal graph design
journal, October 2010
- Choi, Vicky
- Quantum Information Processing, Vol. 10, Issue 3
Rapid object detection using a boosted cascade of simple features
conference, January 2001
- Viola, P.; Jones, M.
- Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001
Quantum annealing in the transverse Ising model
journal, November 1998
- Kadowaki, Tadashi; Nishimori, Hidetoshi
- Physical Review E, Vol. 58, Issue 5
Defining and detecting quantum speedup
journal, June 2014
- Ronnow, T. F.; Wang, Z.; Job, J.
- Science, Vol. 345, Issue 6195
Neuromorphic computing gets ready for the (really) big time
journal, June 2014
- Monroe, Don
- Communications of the ACM, Vol. 57, Issue 6
Partial Deconvolution With Inaccurate Blur Kernel
journal, January 2018
- Ren, Dongwei; Zuo, Wangmeng; Zhang, David
- IEEE Transactions on Image Processing, Vol. 27, Issue 1
Dictionary Learning
journal, March 2011
- Tosic, Ivana; Frossard, Pascal
- IEEE Signal Processing Magazine, Vol. 28, Issue 2
From Point to Set: Extend the Learning of Distance Metrics
conference, December 2013
- Zhu, Pengfei; Zhang, Lei; Zuo, Wangmeng
- 2013 IEEE International Conference on Computer Vision (ICCV)
Adiabatic Quantum Computation and Quantum Annealing: Theory and Practice
journal, July 2014
- McGeoch, Catherine C.
- Synthesis Lectures on Quantum Computing, Vol. 5, Issue 2
Learning the parts of objects by non-negative matrix factorization
journal, October 1999
- Lee, Daniel D.; Seung, H. Sebastian
- Nature, Vol. 401, Issue 6755
D-Wave upgrade: How scientists are using the world’s most controversial quantum computer
journal, January 2017
- Gibney, Elizabeth
- Nature, Vol. 541, Issue 7638
Fast clique minor generation in Chimera qubit connectivity graphs
journal, October 2015
- Boothby, Tomas; King, Andrew D.; Roy, Aidan
- Quantum Information Processing, Vol. 15, Issue 1
Experimental evaluation of an adiabiatic quantum system for combinatorial optimization
conference, January 2013
- McGeoch, Catherine C.; Wang, Cong
- Proceedings of the ACM International Conference on Computing Frontiers - CF '13
Minor-embedding in adiabatic quantum computation: I. The parameter setting problem
journal, September 2008
- Choi, Vicky
- Quantum Information Processing, Vol. 7, Issue 5
Figures / Tables found in this record: