2000 character limit reached
Image Classification with Rotation-Invariant Variational Quantum Circuits (2403.15031v2)
Published 22 Mar 2024 in quant-ph, cs.CV, and cs.LG
Abstract: Variational quantum algorithms are gaining attention as an early application of Noisy Intermediate-Scale Quantum (NISQ) devices. One of the main problems of variational methods lies in the phenomenon of Barren Plateaus, present in the optimization of variational parameters. Adding geometric inductive bias to the quantum models has been proposed as a potential solution to mitigate this problem, leading to a new field called Geometric Quantum Machine Learning. In this work, an equivariant architecture for variational quantum classifiers is introduced to create a label-invariant model for image classification with $C_4$ rotational label symmetry. The equivariant circuit is benchmarked against two different architectures, and it is experimentally observed that the geometric approach boosts the model's performance. Finally, a classical equivariant convolution operation is proposed to extend the quantum model for the processing of larger images, employing the resources available in NISQ devices.
- A. K. Fedorov, N. Gisin, S. M. Beloussov, and A. I. Lvovsky, “Quantum computing at the quantum advantage threshold: a down-to-business review,” (2022), arXiv:2203.17181 [physics, physics:quant-ph].
- A. Abbas, A. Ambainis, B. Augustino, A. Bärtschi, H. Buhrman, C. Coffrin, G. Cortiana, V. Dunjko, D. J. Egger, B. G. Elmegreen, N. Franco, F. Fratini, B. Fuller, J. Gacon, C. Gonciulea, S. Gribling, S. Gupta, S. Hadfield, R. Heese, G. Kircher, T. Kleinert, T. Koch, G. Korpas, S. Lenk, J. Marecek, V. Markov, G. Mazzola, S. Mensa, N. Mohseni, G. Nannicini, C. O’Meara, E. P. Tapia, S. Pokutta, M. Proissl, P. Rebentrost, E. Sahin, B. C. B. Symons, S. Tornow, V. Valls, S. Woerner, M. L. Wolf-Bauwens, J. Yard, S. Yarkoni, D. Zechiel, S. Zhuk, and C. Zoufal, “Quantum Optimization: Potential, Challenges, and the Path Forward,” (2023), arXiv:2312.02279 [quant-ph].
- R. Au-Yeung, B. Camino, O. Rathore, and V. Kendon, “Quantum algorithms for scientific applications,” (2023), arXiv:2312.14904 [physics, physics:quant-ph].
- B. Aizpurua, P. Bermejo, J. E. Martinez, and R. Orús, “Hacking cryptographic protocols with advanced variational quantum attacks,” (2023), arXiv:2311.02986 [quant-ph] .
- P. Bermejo and R. Orús, Scientific Reports 13, 9840 (2023).
- P. Bermejo and R. Orús, “Variational quantum continuous optimization: a cornerstone of quantum mathematical analysis,” (2022), arXiv:2210.03136 [quant-ph] .
- P. Bermejo, B. Aizpurua, and R. Orús, “Improving gradient methods via coordinate transformations: Applications to quantum machine learning,” (2023), arXiv:2304.06768 [quant-ph] .
- P. Wittek, Quantum machine learning: what quantum computing means todata mining, 1st ed. (Elsevier, AP, Amsterdam, 2014).
- M. Schuld and F. Petruccione, Machine Learning with Quantum Computers, Quantum Science and Technology (Springer International Publishing, Cham, 2021).
- J. Liu, F. Wilde, A. A. Mele, L. Jiang, and J. Eisert, “Stochastic noise can be helpful for variational quantum algorithms,” (2023a), arXiv:2210.06723 [quant-ph].
- Y. Wang and J. Liu, “Quantum Machine Learning: from NISQ to Fault Tolerance,” (2024), arXiv:2401.11351 [quant-ph, stat].
- E. Farhi and H. Neven, “Classification with Quantum Neural Networks on Near Term Processors,” (2018), arXiv:1802.06002 [quant-ph].
- P. Rodriguez-Grasa, Y. Ban, and M. Sanz, “Training embedding quantum kernels with data re-uploading quantum neural networks,” (2024), arXiv:2401.04642 [quant-ph].
- M. Ragone, B. N. Bakalov, F. Sauvage, A. F. Kemper, C. O. Marrero, M. Larocca, and M. Cerezo, “A Unified Theory of Barren Plateaus for Deep Parametrized Quantum Circuits,” (2023a), arXiv:2309.09342 [quant-ph].
- E. Fontana, D. Herman, S. Chakrabarti, N. Kumar, R. Yalovetzky, J. Heredge, S. H. Sureshbabu, and M. Pistoia, “The Adjoint Is All You Need: Characterizing Barren Plateaus in Quantum Ans\”atze,” (2023), arXiv:2309.07902 [quant-ph].
- C.-Y. Park and N. Killoran, Quantum 8, 1239 (2024).
- Q. T. Nguyen, L. Schatzki, P. Braccia, M. Ragone, P. J. Coles, F. Sauvage, M. Larocca, and M. Cerezo, “Theory for Equivariant Quantum Neural Networks,” (2022).
- M. Ragone, P. Braccia, Q. T. Nguyen, L. Schatzki, P. J. Coles, F. Sauvage, M. Larocca, and M. Cerezo, “Representation Theory for Geometric Quantum Machine Learning,” (2023b), arXiv:2210.07980 [quant-ph, stat].
- L. Schatzki, M. Larocca, Q. T. Nguyen, F. Sauvage, and M. Cerezo, “Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networks,” (2022).
- M. M. Bronstein, Joan Bruna, T. Cohen, and P. Veličković, “Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges,” (2021), arXiv:2104.13478 [cs, stat].
- J. Bowles, V. J. Wright, M. Farkas, N. Killoran, and M. Schuld, “Contextuality and inductive bias in quantum machine learning,” (2023), arXiv:2302.01365 [quant-ph].
- C. Tüysüz, S. Y. Chang, M. Demidik, K. Jansen, S. Vallecorsa, and M. Grossi, “Symmetry breaking in geometric quantum machine learning in the presence of noise,” (2024), arXiv:2401.10293 [quant-ph].
- M. T. West, J. Heredge, M. Sevior, and M. Usman, “Provably Trainable Rotationally Equivariant Quantum Machine Learning,” (2023a), arXiv:2311.05873 [quant-ph].
- R. D. P. East, G. Alonso-Linaje, and C.-Y. Park, “All you need is spin: SU(2) equivariant variational quantum circuits based on spin networks,” (2023), arXiv:2309.07250 [cond-mat, physics:quant-ph, stat].
- S. Y. Chang, M. Grossi, B. L. Saux, and S. Vallecorsa, “Approximately Equivariant Quantum Neural Network for $p4m$ Group Symmetries in Images,” (2023), arXiv:2310.02323 [quant-ph].
- V. Vapnik, in Advances in Neural Information Processing Systems, Vol. 4 (Morgan-Kaufmann, 1991).
- B. Davvaz, Groups and Symmetry: Theory and Applications (2021).
- R. Larose and B. Coyle, ArXiv: 2003.01695v1.
- M. Mottonen, J. J. Vartiainen, V. Bergholm, and M. M. Salomaa, “Transformation of quantum states using uniformly controlled rotations,” (2004), arXiv:quant-ph/0407010.
- M. A. Nielsen and I. L. Chuang, Quantum Computation and Quantum Information (2010), 10.1017/CBO9780511976667, publisher: Cambridge University Press ISBN: 9780511976667.
- D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” (2017), arXiv:1412.6980 [cs].
- A. Tharwat, Applied Computing and Informatics 17, 168 (2020), publisher: Emerald Publishing Limited.
- R. C. Gonzalez and R. E. Woods, Digital image processing (Pearson, New York, NY, 2018).
- T. S. Cohen and M. Welling, “Group Equivariant Convolutional Networks,” (2016), arXiv:1602.07576 [cs, stat].
- V. Dumoulin and F. Visin, “A guide to convolution arithmetic for deep learning,” (2018), arXiv:1603.07285 [cs, stat].
- M. Cerezo, M. Larocca, D. García-Martín, N. L. Diaz, P. Braccia, E. Fontana, M. S. Rudolph, P. Bermejo, A. Ijaz, S. Thanasilp, E. R. Anschuetz, and Z. Holmes, “Does provable absence of barren plateaus imply classical simulability? Or, why we need to rethink variational quantum computing,” (2023), arXiv:2312.09121 [quant-ph, stat].
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
