Variable hyperparameterized Gaussian kernel using displaced squeezed vacuum state. (English) Zbl 07903014
Summary: There are machine learning schemes for realizing different types of kernels by quantum states of light. It is particularly interesting to realize a Gaussian kernel due to its wider applicability. A multimode coherent state can generate the Gaussian kernel with a constant value of hyperparameter. However, this constancy has limited the application of the Gaussian kernel when it is applied to complex learning problems. We improve it by introducing a variable hyperparameterized Gaussian kernel with a multimode-displaced squeezed vacuum state. The learning capacity of this kernel is tested with the support vector machines over some synthesized data sets, as well as public benchmark data sets. We establish that the proposed variable hyperparameterized Gaussian kernel offers better accuracy over the constant Gaussian kernel.
References:
| [1] | Schölkopf, Bernhard; Smola, Alexander J., Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond, 2002, MIT Press |
| [2] | Ahmed, Shahnawaz, Classification and reconstruction of optical quantum states with deep neural networks, Phys. Rev. Res., 3, 3, Article 033278 pp., 2021 |
| [3] | Hsieh, Hsien-Yi, Extract the degradation information in squeezed states with machine learning, Phys. Rev. Lett., 128, 7, Article 073604 pp., 2022 |
| [4] | Luo, Yi-Jun; Liu, Jin-Ming; Zhang, Chengjie, Detecting genuine multipartite entanglement via machine learning, Phys. Rev. A, 108, 5, Article 052424 pp., 2023 |
| [5] | Zhang, Lifeng; Chen, Zhihua; Fei, Shao-Ming, Entanglement verification with deep semisupervised machine learning, Phys. Rev. A, 108, 2, Article 022427 pp., 2023 |
| [6] | Dutta, Sanchayan, Quantum circuit design methodology for multiple linear regression, IET Quantum Commun., 1, 2, 55-61, 2020 |
| [7] | Melnikov, Alexey, Quantum machine learning: from physics to software engineering, Adv. Phys. X, 8, 1, Article 2165452 pp., 2023 |
| [8] | Mishra, Nimish, Quantum machine learning: a review and current status, (Data Management, Analytics and Innovation: Proceedings of ICDMAI 2020, Volume 2, 2021), 101-145 |
| [9] | Rebentrost, Patrick; Mohseni, Masoud; Lloyd, Seth, Quantum support vector machine for big data classification, Phys. Rev. Lett., 113, 13, Article 130503 pp., 2014 |
| [10] | Schuld, Maria; Fingerhuth, Mark; Petruccione, Francesco, Implementing a distance-based classifier with a quantum interference circuit, Europhys. Lett., 119, 6, Article 60002 pp., 2017 |
| [11] | Park, Daniel K.; Blank, Carsten; Petruccione, Francesco, The theory of the quantum kernel-based binary classifier, Phys. Lett. A, 384, 21, Article 126422 pp., 2020 · Zbl 1448.81248 |
| [12] | Blank, Carsten, Quantum classifier with tailored quantum kernel, npj Quantum Inf., 6, 1, 41, 2020 |
| [13] | Blank, Carsten, Compact quantum kernel-based binary classifier, Quantum Sci. Technol., 7, 4, Article 045007 pp., 2022 |
| [14] | Aradh Bisarya, et al., Breast cancer detection using quantum convolutional neural networks: a demonstration on a quantum computer, medRxiv (2020) 2020-06. |
| [15] | Schuld, Maria, Supervised quantum machine learning models are kernel methods, 2021, preprint |
| [16] | Schuld, Maria; Killoran, Nathan, Quantum machine learning in feature Hilbert spaces, Phys. Rev. Lett., 122, 4, Article 040504 pp., 2019 |
| [17] | Lloyd, Seth, Quantum embeddings for machine learning, 2020, preprint |
| [18] | Mitarai, Kosuke, Quantum circuit learning, Phys. Rev. A, 98, 3, Article 032309 pp., 2018 |
| [19] | Schuld, Maria, Circuit-centric quantum classifiers, Phys. Rev. A, 101, 3, Article 032308 pp., 2020 |
| [20] | Havlíček, Vojtěch, Supervised learning with quantum-enhanced feature spaces, Nature, 567, 7747, 209-212, 2019 |
| [21] | Killoran, Nathan, Continuous-variable quantum neural networks, Phys. Rev. Res., 1, 3, Article 033063 pp., 2019 |
| [22] | Chatterjee, Rupak; Yu, Ting, Generalized coherent states, reproducing kernels, and quantum support vector machines, 2016, preprint |
| [23] | Li, Long Hin; Zhang, Dan-Bo; Wang, Z. D., Quantum kernels with Gaussian state encoding for machine learning, Phys. Lett. A, 436, Article 128088 pp., 2022 · Zbl 1495.81028 |
| [24] | Bartkiewicz, Karol, Experimental kernel-based quantum machine learning in finite feature space, Sci. Rep., 10, 1, Article 12356 pp., 2020 |
| [25] | Roy, Utpal; Banerji, J.; Panigrahi, P. K., Coherent states of the Pöschl-Teller potential and their revival dynamics, J. Phys. A, Math. Gen., 38, 41, 9115, 2005 · Zbl 1081.81061 |
| [26] | Roy, Utpal, Sub-Planck-scale structures in the Pöschl-Teller potential and their sensitivity to perturbations, Phys. Rev. A, 80, 5, Article 052115 pp., 2009 |
| [27] | Ghosh, Suranjana; Sharma, Raman; Roy, Utpal; Panigrahi, Prasanta K., Mesoscopic quantum superposition of the generalized cat state: a diffraction limit, Phys. Rev. A, 92, 5, Article 053819 pp., 2015 |
| [28] | Kumar, Parvendra; Lee, Ray-Kuang, Sensitivity of sub-Planck structures of mesoscopically superposed coherent states to the thermal reservoirs induced decoherence, Opt. Commun., 394, 23-30, 2017 |
| [29] | Scholkopf, Bernhard, Comparing support vector machines with Gaussian kernels to radial basis function classifiers, IEEE Trans. Signal Process., 45, 11, 2758-2765, 1997 |
| [30] | Vapnik, Vladimir, The support vector method of function estimation, (Nonlinear Modeling: Advanced Black-Box Techniques, 1998, Springer us: Springer us Boston, MA), 55-85 |
| [31] | Yang, Jiawei, Parameter selection of Gaussian kernel SVM based on local density of training set, Inverse Probl. Sci. Eng., 29, 4, 536-548, 2021 · Zbl 07402873 |
| [32] | Laanaya, Hicham, Learning general Gaussian kernel hyperparameters of SVMs using optimization on symmetric positive-definite matrices manifold, Pattern Recognit. Lett., 32, 13, 1511-1515, 2011 |
| [33] | Shaydulin, Ruslan; Wild, Stefan M., Importance of kernel bandwidth in quantum machine learning, Phys. Rev. A, 106, 4, Article 042407 pp., 2022 |
| [34] | Canatar, Abdulkadir, Bandwidth enables generalization in quantum kernel models, 2022, preprint |
| [35] | Caves, Carlton M., Quantum-mechanical noise in an interferometer, Phys. Rev. D, 23, 8, 1693, 1981 |
| [36] | Kim, M. S.; De Oliveira, F. A.M.; Knight, P. L., Properties of squeezed number states and squeezed thermal states, Phys. Rev. A, 40, 5, 2494, 1989 |
| [37] | Glauber, Roy J., Coherent and incoherent states of the radiation field, Phys. Rev., 131, 6, 2766, 1963 · Zbl 1371.81166 |
| [38] | Caves, Carlton M.; Schumaker, Bonny L., New formalism for two-photon quantum optics. I. Quadrature phases and squeezed states, Phys. Rev. A, 31, 5, 3068, 1985 |
| [39] | Agarwal, Girish S., Quantum Optics, 2012, Cambridge University Press |
| [40] | Schumaker, Bonny L.; Caves, Carlton M., New formalism for two-photon quantum optics. II. Mathematical foundation and compact notation, Phys. Rev. A, 31, 5, 3093, 1985 |
| [41] | Schumaker, Bonny L., Quantum mechanical pure states with Gaussian wave functions, Phys. Rep., 135, 6, 317-408, 1986 |
| [42] | Braunstein, Samuel L., Squeezing as an irreducible resource, Phys. Rev. A, 71, 5, Article 055801 pp., 2005 |
| [43] | Boser, Bernhard E.; Guyon, Isabelle M.; Vapnik, Vladimir N., A training algorithm for optimal margin classifiers, (Proceedings of the Fifth Annual Workshop on Computational Learning Theory, 1992) |
| [44] | (Schölkopf, Bernhard; Burges, Christopher JC; Smola, Alexander J., Advances in Kernel Methods: Support Vector Learning, 1999, MIT Press) |
| [45] | Hearst, Marti A., Support vector machines, IEEE Intell. Syst. Appl., 13, 4, 18-28, 1998 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
