Abstract
Before coming to the design of quantum machine learning algorithms, this chapter is an interlude to discuss how quantum computing can actually assist machine learning. Although quantum computing researchers often focus on asymptotic computational speedups, there is more than one measure of merit when it comes to machine learning. We will discuss three dimensions here, namely the computational complexity, the sample complexityand the model complexity. While the section on computational complexity allows us to establish the terminology already used in previous chapters with more care, the section on sample complexity ventures briefly into quantum extensions of statistical learning theory. The last section on model complexity provides arguments towards what has been called the exploratory approach to quantum machine learning, in which quantum physics is used as a resource to build new types of models altogether.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The three dimensions were first introduced by Peter Wittek and Vedran Dunjko.
- 2.
Applying a quantum Fourier transform effectively changes the distribution from which to sample, which leaves some question whether the comparison to a static ‘classical example generator’ is fair. However, they show that while the quantum example oracle can be simulated by a membership query oracle, this is not true vice versa. It seems therefore that the quantum example oracle ranges somewhere between a query and an example oracle.
References
Bernstein, E., Vazirani, U.: Quantum complexity theory. SIAM J. Comput. 26(5), 1411–1473 (1997)
Watrous, J.: Quantum computational complexity. In: Encyclopedia of Complexity and Systems Science, pp. 7174–7201. Springer (2009)
Rãnnow, T.F., Wang, Z., Job, J., Boixo, S., Isakov, S.V., Wecker, D., Martinis, J.M., Lidar, D.A., Troyer, M.: Defining and detecting quantum speedup. Science 345, 420–424 (2014)
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. ACM (1996)
Bennett, C.H., Bernstein, E., Brassard, G., Vazirani, U.: Strengths and weaknesses of quantum computing. SIAM J. Comput. 26(5), 1510–1523 (1997)
Steiger, D.S., Troyer, M.: Racing in parallel: quantum versus classical. In: Bulletin of the American Physical Society, vol. 61 (2016)
Sammut, C., Webb, G.I.: Encyclopedia of Machine Learning. Springer Science & Business Media (2011)
Neven, H., Denchev, V.S., Rose, G., Macready, W.G.: Training a large scale classifier with the quantum adiabatic algorithm. arXiv:0912.0779 (2009)
Amin, M.H.: Searching for quantum speedup in quasistatic quantum annealers. Phys. Rev. A 92(5), 1–6 (2015)
Vapnik, V.N., Vapnik, V.: Statistical learning theory, vol. 1. Wiley, New York (1998)
Arunachalam, S., de Wolf, R.: Guest column: a survey of quantum learning theory. ACM SIGACT News 48(2), 41–67 (2017)
Angluin, D.: Queries and concept learning. Mach. Learn. 2(4), 319–342 (1988)
Valiant, L.G.: A theory of the learnable. Commun. ACM 27(11), 1134–1142 (1984)
Rocco, A.S., Gortler, S.J.: Equivalences and separations between quantum and classical learnability. SIAM J. Comput. 33(5), 1067–1092 (2004)
Hunziker, M., Meyer, D.A., Park, J., Pommersheim, J., Rothstein, M.: The geometry of quantum learning. Quant. Inf. Process. 9(3), 321–341 (2010)
Ambainis, A., Iwama, K., Kawachi, A., Masuda, H., Putra, R.H., Yamashita, S.: Quantum identification of Boolean oracles. In: Annual Symposium on Theoretical Aspects of Computer Science, pp. 105–116. Springer (2004)
Atici, A., Servedio, R.A.: Improved bounds on quantum learning algorithms. Quant. Inf. Process. 4(5), 355–386 (2005)
Kothari, R.: An optimal quantum algorithm for the oracle identification problem. In: Proceedings of the 31st International Symposium on Theoretical Aspects of Computer Science (STACS 2014), Leibniz International Proceedings in Informatics, vol. 25, pp. 482–493 (2014)
Blumer, A., Ehrenfeucht, A., Haussler, D., Warmuth, M.K.: Learnability and the Vapnik-Chervonenkis dimension. J. ACM (JACM) 36(4), 929–965 (1989)
Hanneke, S.: The optimal sample complexity of PAC learning. J. Mach. Learn. Res. 17(38), 1–15 (2016)
Bshouty, N.H., Jackson, J.C.: Learning DNF over the uniform distribution using a quantum example oracle. SIAM J. Comput. 28(3), 1136–1153 (1998)
Arunachalam, S., de Wolf, R.: Optimal quantum sample complexity of learning algorithms. arXiv:1607.00932 (2016)
Cross, A.W., Smith, G., Smolin, J.A.: Quantum learning robust against noise. Phys. Rev. A 92(1), 012327 (2015)
Schölkopf, B., Herbrich, R., Smola, A.: A generalized representer theorem. In: Computational Learning Theory, pp. 416–426. Springer (2001)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Schuld, M., Petruccione, F. (2018). Quantum Advantages. In: Supervised Learning with Quantum Computers. Quantum Science and Technology. Springer, Cham. https://doi.org/10.1007/978-3-319-96424-9_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-96424-9_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-96423-2
Online ISBN: 978-3-319-96424-9
eBook Packages: Physics and AstronomyPhysics and Astronomy (R0)