Abstract
Quantum kernel methods have become a viable option for high-dimensional data classification with the computation power of quantum systems. Fundamentally, classical kernel methods (e.g., support vector machines) have been shown to be effective by mapping data into higher-dimensional, explicitly defined feature spaces where linear reparability is achieved. But when data dimensionality becomes large, classical methods encounter issues of computational feasibility and scalability. Addressing these challenges, quantum kernel methods involve mapping the data onto quantum feature spaces by encoding them in terms of quantum states processed on quantum circuits. This allows for efficient representation and manipulation of complicated data distributions.
In this paper, we study the theory, practice and advantages of quantum kernel methods for high-dimensional classification. It addresses quantum feature mapping methods, kernel estimation with quantum circuits, and hybrid quantum–classical learning frameworks Empirical evidence shows that quantum kernels can improve classification performance for certain tasks, especially when classical kernels fail to capture complex correlations. The paper alludes to real-world issues, including noise, the need for a ton of quits and hardware limitations. But all of this is beside the point: quantum kernel methods mark a major advance to realizing at least some aspects of quantum advantage in machine learning and which open up exciting possibilities for solving complex classification problems arising in real-world applications.
Reference
[1] Nielsen, M.A. and Chuang, I.L., 2010. Quantum Computation and Quantum Information. Cambridge: Cambridge University Press.
[2] Reskill, J., 2018. Quantum computing in the NISQ era and beyond. Quantum, 2, p.79.
[3] Belmonte, J., Witter, P., Pancetta, N., Rebentrost, P., Weise, N. and Lloyd, S., 2017. Quantum machine learning. Nature, 549(7671), pp.195–202.
[4] Schulz, M. and Petruccione, F., 2018. Supervised Learning with Quantum Computers. Cham: Springer.
[5] Havelock, V. et al., 2019. Supervised learning with quantum-enhanced feature spaces. Nature, 567(7747), pp.209–212.
[6] Rebentrost, P., Mohsen, M. and Lloyd, S., 2014. Quantum support vector machine for big data classification. Physical Review Letters, 113(13). v
[7] Lloyd, S., Mohsen, M. and Rebentrost, P., 2014. Quantum machine learning. Nature Physics, 10(9), pp.631–633.
[8] Benedetti, M., Lloyd, E., Sack, S. and Florentine, M., 2019. Parameterized quantum circuits as machine learning models. Quantum Science and Technology, 4(4).
[9] Schulz, M., Sweke, R. and Meyer, J.J., 2021. Effect of data encoding on quantum machine learning. Physical Review A, 103(3).
[10] Abbas, A. et al., 2021. The power of quantum neural networks. Nature Computational Science, 1(6), pp.403–409.
[11] Carazo, M. et al., 2021. Variational quantum algorithms. Nature Reviews Physics, 3(9), pp.625–644.
[12] McLean, J.R. et al., 2018. Barren plateaus in quantum neural network training landscapes. Nature Communications, 9(1).
[13] Schulz, M. and Kilogram, N., 2019. Quantum machine learning in feature Hilbert spaces. Physical Review Letters, 122(4).
[14] Huang, H.Y. et al., 2021. Power of data in quantum machine learning. Nature Communications, 12.
[15] Carlo, G. and Troyer, M., 2017. Solving the quantum many-body problem with machine learning. Science, 355(6325), pp.602–606.
[16] Dunk, V. and Brie gel, H.J., 2018. Machine learning and artificial intelligence in the quantum domain. Reports on Progress in Physics, 81(7).
[17] Broughton, M. et al., 2020. Tensor Flow Quantum. Nature, 589.
[18] Kilogram, N. et al., 2019. Continuous-variable quantum neural networks. Physical Review Research, 1(3).
[19] Arête, F. et al., 2019. Quantum supremacy using a programmable superconducting processor. Nature, 574.
[20] Mandala, A. et al., 2017. Hardware-efficient Variational quantum Eigen solver. Nature, 549.
[21] Time, K., Bray, S. and Gambetta, J.M., 2017. Error mitigation for short-depth quantum circuits. Physical Review Letters, 119(18).
[22] Endo, S., Benjamin, S.C. and Li, Y., 2018. Practical quantum error mitigation. Physical Review X, 8(3).
[23] Li, Y. and Benjamin, S.C., 2017. Efficient Variational quantum simulator. Physical Review X, 7(2).
[24] Harrow, A.W., Hassidim, A. and Lloyd, S., 2009. Quantum algorithm for linear systems of equations. Physical Review Letters, 103(15).
[25] Grover, L.K., 1996. A fast quantum mechanical algorithm for database search. STOC.
[26] Short, P.W., 1994. Algorithms for quantum computation. FOCS.
[27] Aaronson, S., 2013. Quantum Computing Since Democritus. Cambridge University Press.
[28] Cao, Y. et al., 2019. Quantum chemistry in the age of quantum computing. Chemical Reviews, 119(19).
[29] Tang, E., 2019. Quantum-inspired classical algorithms. STOC.
[30] Good fellow, I., Bagnio, Y. and Carville, A., 2016. Deep Learning. MIT Press.
[31] Bagnio, Y., 2013. Representation learning: A review. IEEE TPAMI, 35(8).
[32] Hinton, G.E. and Salakhutdinov, R.R., 2006. Reducing dimensionality with neural networks. Science, 313(5786).
[33] Krizhevsky, A., Sutskever, I. and Hinton, G.E., 2012. Image Net classification with deep CNNs. NIPS.
[34] Aswan, A. et al., 2017. Attention is all you need. Neutrals.
[35] IBM, 2021. Qi skit Documentation. Available at: https://qiskit.org
[36] Microsoft, 2022. Quantum Development Kit. Available at: https://learn.microsoft.com
[37] Google AI Quantum, 2019. Quantum processor research. Nature.
[38] NIST, 2022. Post-Quantum Cryptography Standardization.
[39] IEEE, 2024. Quantum computing research and standards.
[40] World Economic Forum, 2022. Quantum computing governance principles.
[41] Schulz, M., 2021. Supervised quantum machine learning models. arrive.
[42] Gilberto, C., Herter, M., Along, A.D., Postil, M., Brochette, A., Severing, S. and Bossing, L., 2018. Quantum machine learning: a classical perspective. Proceedings of the Royal Society A.
[43] Witter, P., 2014. Quantum Machine Learning: What Quantum Computing Means to Data Mining. Academic Press.
[44] Weise, N., Kapok, A. and Sore, K.M., 2014. Quantum algorithms for nearest-neighbour methods. Quantum Information & Computation.
[45] Farsi, E. and Even, H., 2018. Classification with quantum neural networks. Arrive.
[46] Mitral, K., Ngoro, M., Kitagawa, M. and Fuji, K., 2018. Quantum circuit learning. Physical Review A.
[47] Schulz, M. and Petruccione, F., 2020. Machine learning with quantum computers. Quantum Science and Technology.
[48] Meyer, J.J., Schulz, M., 2020. Information content of quantum states. PRX Quantum.
[49] Benedetti, M. et al., 2020. A generative modelling approach for benchmarking quantum circuits. NPJ Quantum Information.
[50] Huang, H.Y., Keung, R. and Reskill, J., 2021. Predicting many properties of a quantum system. Nature Physics.