Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Adiabatic Quantum Support Vector Machines (2401.12485v1)

Published 23 Jan 2024 in cs.LG, cs.AI, quant-ph, and stat.ML

Abstract: Adiabatic quantum computers can solve difficult optimization problems (e.g., the quadratic unconstrained binary optimization problem), and they seem well suited to train machine learning models. In this paper, we describe an adiabatic quantum approach for training support vector machines. We show that the time complexity of our quantum approach is an order of magnitude better than the classical approach. Next, we compare the test accuracy of our quantum approach against a classical approach that uses the Scikit-learn library in Python across five benchmark datasets (Iris, Wisconsin Breast Cancer (WBC), Wine, Digits, and Lambeq). We show that our quantum approach obtains accuracies on par with the classical approach. Finally, we perform a scalability study in which we compute the total training times of the quantum approach and the classical approach with increasing number of features and number of data points in the training dataset. Our scalability results show that the quantum approach obtains a 3.5--4.5 times speedup over the classical approach on datasets with many (millions of) features.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (47)
  1. Learning from data, volume 4. AMLBook New York, NY, USA:, 2012.
  2. Application of quantum annealing to training of deep neural networks. arXiv preprint arXiv:1510.06356, 2015.
  3. Quantum Boltzmann machine. Physical Review X, 8(2):021050, 2018.
  4. Balanced k-means clustering on an adiabatic quantum computer. Quantum Information Processing, 20(9):1–30, 2021.
  5. Quantum supremacy using a programmable superconducting processor. Nature, 574(7779):505–510, 2019.
  6. Using machine learning for quantum annealing accuracy prediction. Algorithms, 14(6), 2021. ISSN 1999-4893. doi: 10.3390/a14060187. URL https://www.mdpi.com/1999-4893/14/6/187.
  7. Parameterized quantum circuits as machine learning models. Quantum Science and Technology, 4(4):043001, 2019.
  8. Quantum machine learning. Nature, 549(7671):195–202, 2017.
  9. Support vector machine solvers. Large scale kernel machines, 3(1):301–320, 2007.
  10. Coppersmith, D. An approximate fourier transform useful in quantum factoring. arXiv preprint quant-ph/0201067, 2002.
  11. Date, P. Combinatorial Neural Network Training Algorithm for Neuromorphic Computing. PhD thesis, Rensselaer Polytechnic Institute, 2019.
  12. Adiabatic quantum linear regression. Scientific reports, 11(1):21905, 2021.
  13. Quantum discriminator for binary classification. Scientific Reports, 14(1):1328, 2024.
  14. Efficiently embedding QUBO problems on adiabatic quantum computers. Quantum Information Processing, 18(4):117, 2019a.
  15. A classical-quantum hybrid approach for unsupervised probabilistic machine learning. In Future of Information and Communication Conference, pp. 98–117. Springer, 2019b.
  16. Qubo formulations for training machine learning models. Scientific Reports, 11, 2021.
  17. Quantum computing for data analysis in high energy physics. arXiv preprint arXiv:2203.08805, 2022.
  18. Machine learning & artificial intelligence in the quantum domain: a review of recent progress. Reports on Progress in Physics, 81(7):074001, 2018.
  19. Quantum-enhanced machine learning. Physical review letters, 117(13):130501, 2016.
  20. Optimizing quantum optimization algorithms via faster quantum gradient computation. In Proceedings of the Thirtieth Annual ACM-SIAM Symposium on Discrete Algorithms, pp.  1425–1444. SIAM, 2019.
  21. Grover, L. K. A fast quantum mechanical algorithm for database search. In Proceedings of the twenty-eighth annual ACM symposium on Theory of computing, pp.  212–219, 1996.
  22. Quantum algorithm for linear systems of equations. Physical review letters, 103(15):150502, 2009.
  23. Supervised learning with quantum-enhanced feature spaces. Nature, 567(7747):209–212, 2019.
  24. Snowmass white paper: Quantum computing systems and software for high-energy physics research. arXiv preprint arXiv:2203.07091, 2022.
  25. Jordan, S. P. Fast quantum algorithm for numerical gradient estimation. Physical review letters, 95(5):050501, 2005.
  26. Karush, W. Minima of functions of several variables with inequalities as side constraints. M. Sc. Dissertation. Dept. of Mathematics, Univ. of Chicago, 1939.
  27. The unconstrained binary quadratic programming problem: a survey. Journal of Combinatorial Optimization, 28(1):58–81, 2014.
  28. Nonlinear programming. In Traces and emergence of nonlinear programming, pp. 247–258. Springer, 2014.
  29. Deep learning. Nature, 521(7553):436–444, 2015.
  30. Effective QUBO modeling for solving linear systems on D-wave quantum annealing device. In Donkor, E., Hayduk, M., Frey, M. R., Jr., S. J. L., and Myers, J. M. (eds.), Quantum Information Science, Sensing, and Computation XIV, volume 12093, pp.  120930F. International Society for Optics and Photonics, SPIE, 2022. doi: 10.1117/12.2632416. URL https://doi.org/10.1117/12.2632416.
  31. Sublinear quantum algorithms for training linear and kernel-based classifiers. In Chaudhuri, K. and Salakhutdinov, R. (eds.), Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, pp.  3815–3824, Long Beach, California, USA, 09–15 Jun 2019. PMLR. URL http://proceedings.mlr.press/v97/li19b.html.
  32. Lucas, A. Ising formulations of many np problems. Frontiers in Physics, 2:5, 2014.
  33. Quantum optimization using variational algorithms on near-term quantum devices. Quantum Science and Technology, 3(3):030503, 2018.
  34. Multivariable optimization: Quantum annealing and computation. The European Physical Journal Special Topics, 224(1):17–24, 2015.
  35. Munson, M. A. A study on the importance of and time spent on different modeling steps. ACM SIGKDD Explorations Newsletter, 13(2):65–71, 2012.
  36. QBoost: Large scale classifier training with adiabatic quantum optimization. In Hoi, S. C. H. and Buntine, W. (eds.), Proceedings of the Asian Conference on Machine Learning, volume 25 of Proceedings of Machine Learning Research, pp.  333–348, Singapore Management University, Singapore, 04–06 Nov 2012. PMLR. URL http://proceedings.mlr.press/v25/neven12.html.
  37. Coreset of hyperspectral images on a small quantum computer. In IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium, pp.  4923–4926, 2022. doi: 10.1109/IGARSS46834.2022.9884273.
  38. Opportunities and challenges for quantum-assisted machine learning in near-term quantum computers. Quantum Science and Technology, 3(3):030502, 2018.
  39. Quantum adiabatic machine learning. Quantum information processing, 12(5):2027–2070, 2013.
  40. Discriminating quantum states with quantum machine learning. In 2021 International Conference on Rebooting Computing (ICRC), pp.  56–63. IEEE, 2021.
  41. Quantum gradient descent and newton’s method for constrained polynomial optimization. New Journal of Physics, 21(7):073023, 2019.
  42. Circuit-centric quantum classifiers. arXiv preprint arXiv:1804.00633, 2018.
  43. Shor, P. W. Algorithms for quantum computation: discrete logarithms and factoring. In Proceedings 35th annual symposium on foundations of computer science, pp.  124–134. Ieee, 1994.
  44. Experimental evaluation of quantum machine learning algorithms. IEEE Access, 11:6197–6208, 2023. doi: 10.1109/ACCESS.2023.3236409.
  45. The end of moore’s law: A new beginning for information technology. Computing in Science & Engineering, 19(2):41–50, 2017.
  46. Simulated versus reduced noise quantum annealing in maximum independent set solution to wireless network scheduling. Quantum Information Processing, 18(1):1–25, 2019.
  47. Support vector machines on the D-Wave quantum annealer. Computer Physics Communications, pp.  107006, 2019.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now