Hostname: page-component-77c89778f8-m42fx Total loading time: 0 Render date: 2024-07-18T14:43:53.892Z Has data issue: false hasContentIssue false
  • English
  • Français

Learning quantum finite automata with queries

Published online by Cambridge University Press:  30 November 2023

Daowen Qiu Open the ORCID record for Daowen Qiu [Opens in a new window]
Daowen Qiu*
Affiliation:
Institute of Quantum Computing and Computer Theory, School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510006, China The Guangdong Key Laboratory of Information Security Technology, Sun Yat-sen University, Guangzhou 510006, China
*
Email: issqdw@mail.sysu.edu.cn
Get access Rights & Permissions [Opens in a new window]

Abstract

Learning finite automata (termed as model learning) has become an important field in machine learning and has been useful realistic applications. Quantum finite automata (QFA) are simple models of quantum computers with finite memory. Due to their simplicity, QFA have well physical realizability, but one-way QFA still have essential advantages over classical finite automata with regard to state complexity (two-way QFA are more powerful than classical finite automata in computation ability as well). As a different problem in quantum learning theory and quantum machine learning, in this paper, our purpose is to initiate the study of learning QFA with queries (naturally it may be termed as quantum model learning), and the main results are regarding learning two basic one-way QFA (1QFA): (1) we propose a learning algorithm for measure-once 1QFA (MO-1QFA) with query complexity of polynomial time and (2) we propose a learning algorithm for measure-many 1QFA (MM-1QFA) with query complexity of polynomial time, as well.

Keywords

quantum computingquantum finite automatalearning from queriesquantum model learningSD oracles
Type
Paper
Information
Mathematical Structures in Computer Science , Volume 34 , Issue 2 , February 2024 , pp. 128 - 146
Check for updates
Copyright
© The Author(s), 2023. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Aaronson, S. (2007). The learnability of quantum states. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences 463 (2088) 3089–3114.CrossRefGoogle Scholar
Angluin, D. (1982). Queries and concept learning. Journal of the ACM 29 (3) 741–765.CrossRefGoogle Scholar
Angluin, D. (1987). Learning regular sets from queries and counterexamples. Information and Computation 75 (2) 87–106.CrossRefGoogle Scholar
Angluin, D. (1988). Queries and concept learning. Machine Learning 2 (4) 319–342.CrossRefGoogle Scholar
Ambainis, A., Beaudry, M., Golovkins, M., Kikusts, A., Mercer, M. and Therien, D. (2006). Algebraic results on quantum automata. Theory of Computing Systems 39 (1) 165–188.CrossRefGoogle Scholar
Avron, J., Casper, O. and Rozen, I. (2021). Quantum advantage and noise reduction in distribute quantum computing. Physical Review A 104 052404.CrossRefGoogle Scholar
Angluin, D., Eisenstat, S. and Fisman, D. 2015. Learning regular languages via alternating automata. In: Proceeding of the 24th International Joint Conference on Artificial Intelligence, IJCAI 2015, AAAI Press, 3308–3314.Google Scholar
Ambainis, A. and Freivalds, R. (1998). One-way quantum finite automata: Strengths, weaknesses and generalizations. In: Proceeding of the 39th Foundations of Computer Science, FOCS 1998, IEEE Computer Society Press, 332–341.Google Scholar
Arunachalam, S. and de Wolf, R. (2017). A survey of quantum learning theory. ACM SIGACT News 48 (2) 41–67. Also, arXiv:1701.06806v3.CrossRefGoogle Scholar
Arunachalam, S. and de Wolf, R. (2018). Optimal quantum sample complexity of learning algorithms. Journal of Machine Learning Research 19 1–36.Google Scholar
Ambainis, A. and Yakaryilmaz, A. (2021). Automata and quantum computing. In: Pin, J.-E. (ed.) Handbook of Automata Theory (II), 1457–1493. arXiv:1507.01988.Google Scholar
Belovs, A. (2015). Quantum algorithms for learning symmetric juntas via the adversary bound. Computational Complexity 24 (2) 255–293.CrossRefGoogle Scholar
Bollig, B., Habermehl, P., Kern, C. and Leucker, M. (2009). Angluin-style learning of NFA. In: Proceeding of the 21st International Joint Conference on Artificial Intelligence, IJCAI-09, AAAI Press, 1004–1009.Google Scholar
Bshouty, N. H. and Jackson, J. C. (1999). Learning DNF over the uniform distribution using a quantum example oracle. SIAM Journal on Computing 28 (3) 1136–1153. Earlier version in COLT’95.CrossRefGoogle Scholar
Bhatia, A. S. and Kumar, A. (2019). Quantum Finite Automata: Survey, Status and Research Directions, arXiv:1901.07992v1.Google Scholar
Berndt, S., Liśkiewicz, M., Lutter, M. and Reischuk, R. (2017). Learning residual alternating automata. In: Proceeding of the 31st AAAI Conference on Artificial Intelligence, AAAI-17, AAAI Press, 1749–1755.CrossRefGoogle Scholar
Benedetti, M., Lloyd, E., Sack, S. and Fiorentini, M. (2019). Parameterized quantum circuits as machine learning models. Quantum Science and Technology 4 (4), 043001.CrossRefGoogle Scholar
Balle, B. and Mohri, M. (2015). Learning weighted automata. In: Maletti, A. (ed.) Algebraic Informatics. CAI 2015, LNCS, vol. 9270, Springer, 1–21.CrossRefGoogle Scholar
Bertoni, A., Mereghetti, C. and Palano, B. (2003). Quantum computing: 1-way quantum automata. In: Proceeding of the 7th International Conference on Developments in Language Theory, DLT 2003, Springer, 1–20.CrossRefGoogle Scholar
Brodsky, A. and Pippenger, N. (2002). Characterizations of 1-way quantum finite automata. SIAM Journal on Computing 31 (5) 1456–1478.CrossRefGoogle Scholar
Bergadano, F. and Varricchio, S. (1996). Learning behaviors of automata from multiplicity and equivalence queries. SIAM Journal on Computing 25 (6) 1268–1280.CrossRefGoogle Scholar
Boyd, S. and Vandenberghe, L. (2004). Convex Optimization, Cambridge University Press.CrossRefGoogle Scholar
Biamonte, J., Wittek, P., Pancotti, N., Rebentrost, P., Wiebe, N. and Lloyd, S. (2017). Quantum machine learning. Nature 549 (7671) 195–202.CrossRefGoogle ScholarPubMed
Cong, I. and Duan, L. (2016). Quantum discriminant analysis for dimensionality reduction and classification. New Journal of Physics 18 (7) 073011.CrossRefGoogle Scholar
Cheng, H.C., Hsieh, M. H. and Yeh, P. C. (2016). The learnability of unknown quantum measurements. Quantum Information & Computation 16 (7&8) 615–656.CrossRefGoogle Scholar
Faddeev, D. K. and Faddeev, V. N. (1963). Computational Methods of Linear Algebra, Freeman.Google Scholar
Gavinsky, D. ((2012)). Quantum predictive learning and communication complexity with single input. Quantum Information & Computation 12 (7&8) 575–588.CrossRefGoogle Scholar
Gruska, J. (1999). Quantum Computing, McGraw-Hill.Google Scholar
de la Higuera, C. (2005). A bibliographical study of grammatical inference. Pattern Recognition, 38 (9) 1332–1348.CrossRefGoogle Scholar
de la Higuera, C. (2010). Grammatical Inference: Learning Automata and Grammars, Cambridge University Press.CrossRefGoogle Scholar
Huang, H. Y., Broughton, M. and Cotler, J. (2022). Quantum advantage in learning from experiments. Science 376 (6598) 1182–1186.CrossRefGoogle ScholarPubMed
Harrow, A. W., Hassidim, A. and Lloyd, S. (2009). Quantum algorithm for linear systems of equations. Physical Review Letters 103 (5) 150502.CrossRefGoogle ScholarPubMed
Karmarkar, N. (1984). A new polynomial-time algorithm for linear programming. Combinatorica 4 373–395.CrossRefGoogle Scholar
Kerenidis, I. and Prakash, A. (2017). Quantum recommendation systems. Innovations in Theoretical Computer Science Conference 49 1–21.Google Scholar
Krenn, M., Landgraf, J., Foesel, T. and Marquardt, F. (2023). Artificial intelligence and machine learning for quantum technologies. Physical Review A 107 (1) 010101.CrossRefGoogle Scholar
Kearns, M. J. and Vazirani, U. V. (1994). An Introduction to Computational Learning Theory, MIT Press.CrossRefGoogle Scholar
Kondacs, A. and Watrous, J. (1997). On the power of quantum finite state automata. In: Proceedings of the 38th Annual IEEE Symposium on Foundations of Computer Science, FOCS 97, IEEE Computer Society Press, 66–75.CrossRefGoogle Scholar
Lloyd, S., Mohseni, M. and Rebentrost, P. (2014). Quantum principal component analysis. Nature Physics 10 (9) 108–113.CrossRefGoogle Scholar
Li, L. and Qiu, D. W. (2006). Determination of equivalence between quantum sequential machines. Theoretical Computer Science 358 65–74.CrossRefGoogle Scholar
Li, L. and Qiu, D. W. (2008). Determining the equivalence for one-way quantum finite automata. Theoretical Computer Science 403 42–51.CrossRefGoogle Scholar
Lloyd, S. and Weedbrook, C. (2018). Quantum generative adversarial learning. Physical Review Letters 121 (4) 040502.CrossRefGoogle ScholarPubMed
Marquardt, F. (2021). Machine learning and quantum devices. SciPost Physics Lecture Notes 029.CrossRefGoogle Scholar
Moore, E. (1956). Gedanken-experiments on sequential machines. Automata Studies, Annals of Mathematics Studies 34 129–153.Google Scholar
Moore, C. and Crutchfield, J. P. (2000). Quantum automata and quantum grammars. Theoretical Computer Science 237 275–230.CrossRefGoogle Scholar
Meyer, J. J., Mularski, M., Gil-Fuster, E., Mele, A. A., Arzani, F., Wilms, A. and Eisert, J. (2023). Exploiting symmetry in variational quantum machine learning. PRX Quantum 4 (1) 010328.CrossRefGoogle Scholar
Mitarai, K., Negoro, M., Kitagawa, M. and Fujii, K. (2018). Quantum circuit learning. Physical Review A 98 (3) 032309.CrossRefGoogle Scholar
Mereghetti, C., Palano, B., Cialdi, S. et al. (2020). Photonic realization of a quantum finite automaton. Physical Review Research 2 Art. no. 013089.CrossRefGoogle Scholar
Mereghetti, C., Palano, B., Cialdi, S., Vento, V., Paris, M. G. A. and Olivares, S. (2020). Photonic realization of a quantum finite automaton. Physical Review Research 2 013089 (15 pages).CrossRefGoogle Scholar
Mateus, P., Qiu, D. W. and Li, L. (2012). On the complexity of minimizing probabilistic and quantum automata. Information and Computation 218 36–53.CrossRefGoogle Scholar
Nielsen, M. and Chuang, I. (2000). Quantum Computation and Quantum Information, Cambridge University Press.Google Scholar
Paschen, K. (2000). Quantum Finite Automata using Ancilla Qubits, University of Karlsruhe, Technical report.Google Scholar
Paz, A. (1971). Introduction to Probabilistic Automata, Academic Press.Google Scholar
Plachta, S. Z. D., Hiekkamäki, M., Yakaryilmaz, A. and Fickler, R. (2022). Quantum advantage using high-dimensional twisted photons as quantum finite automata. Quantum-Austria 6 752.CrossRefGoogle Scholar
Peled, D., Vardi, M. and Yannakakis, M. (2002). Black box checking. Journal of Automata Languages & Combinatorics 7 (2) 225–246.Google Scholar
Qiu, D. W. (2007). Automata theory based on quantum logic: Reversibilities and pushdown automata. Theoretical Computer Science 386 (1–2) 38–56.CrossRefGoogle Scholar
Qiu, D. W., Li, L., Mateus, P. and Gruska, J. (2012). Quantum Finite Automata. In: Wang, J. (ed.) Finite State-Based Models and Applications, CRC Handbook, 113–144.Google Scholar
Qiu, D. W., Li, L., Mateus, P. and Sernadas, A. (2015). Exponentially more concise quantum recognition of non-RMM languages. Journal of Computer and System Sciences 81 (2) 359–375.CrossRefGoogle Scholar
Qiu, D. W., Luo, L. and Xiao, L. (2022). Distributed Grover’s Algorithm, arXiv:2204.10487v4.Google Scholar
Qiu, D. W., Li, L., Zou, X., Mateus, P. and Gruska, J. (2011). Multi-letter quantum finite automata: Decidability of the equivalence and minimization of states. Acta Informatica 48 271–290.CrossRefGoogle Scholar
Qiu, D. W. and Yu, S. (2009). Hierarchy and equivalence of multi-letter quantum finite automata. Theoretical Computer Science 410 3006–3017.CrossRefGoogle Scholar
Rebentrost, P., Mohseni, M. and Lloyd, S. (2014). Quantum support vector machine for big data classification. Physical Review Letters 113 (13) 130503.CrossRefGoogle ScholarPubMed
Rodriguez, L. E. H., Ullah, A., Espinosa, K. J. R., Dral, P. O. and Kananenka, A. A. (2022). A comparative study of different machine learning methods for dissipative quantum dynamics. Machine Learning: Science and Technology 3 (4) 045016.Google Scholar
Schuld, M., Sinayskiy, I. and Petruccione, F. (2015). An introduction to quantum machine learning. Contemporary Physics 56 (2) 172–185.CrossRefGoogle Scholar
Say, A. C. and Yakarylmaz, A. (2014). Quantum finite automata: A modern introduction. In: Computing with New Resources, Springer, 208–222.CrossRefGoogle Scholar
Servedio, R. and Gortler, S. (2004). Equivalences and separations between quantum and classical learnability. SIAM Journal on Computing 33 (5) 1067–1092.CrossRefGoogle Scholar
Tzeng, W. G. (1992). Learning probabilistic automata and Markov chains via queries. Machine Learning 8 (2) 151–166.CrossRefGoogle Scholar
Tian, Y., Feng, T., Luo, M., Zheng, S. and Zhou, X. (2019). Experimental demonstration of quantum finite automaton. NPJ Quantum Information 5 (1) 1–5.CrossRefGoogle Scholar
Tîrna˘uca˘, C. and Knuutila, T. (2007). Polynomial time algorithms for learning k-reversible languages and pattern languages with correction queries. In: Hutter, M., Servedio, R. , and Takimoto, E. (eds.) Algorithmic Learning Theory: 18th International Conference, ALT’ 2007, Lecture Notes in Artificial Intelligence, vol. 4754, Springer-Verlag, 272–284.Google Scholar
Vaandrager, F. (2017). Model learning. Communications of the ACM 60 (2) 86–95.CrossRefGoogle Scholar
Wiebe, N., Braun, D. and Lloyd, S. (2012). Quantum algorithm for data fitting. Physical Review Letters 109 (5) 050505.CrossRefGoogle ScholarPubMed
Wiebe, N., Kapoor, A. and Svore, K. (2016). Quantum deep learning. Quantum Information & Computation 16 (7) 541–587.CrossRefGoogle Scholar
Zhang, C. (2010). An improved lower bound on query complexity for quantum PAC learning. Information Processing Letters 111 (1) 40–45.CrossRefGoogle Scholar
Zhao, Z. Pozas-Kerstjens, A., Rebentrost, P. and Wittek, P. (2019). Bayesian deep learning on a quantum computer. Quantum Machine Intelligence 1 41–51.CrossRefGoogle Scholar