Abstract
We take a closer look on the complexity landscape of one of the most fundamental and well-studied problems in computational learning theory: the problem of learning a finite automaton A consistent with a set \(P\) of positive examples and with a set \(N\) of negative examples. By consistency, we mean that A accepts all strings in \(P\) and rejects all strings in \(N\). It is well known that this problem is NP-hard when parameterized only by the number of states of the automaton. Therefore, our analysis takes a more refined parameterization: we consider the number k of states in A, the size \(|\varSigma |\) of the alphabet, the maximum size l of a string in \(P\cup N\), and the number \(c=|P\cup N|\) of strings in both sets. First, we prove several Pvs. NP-hard dichotomy results for these parameters when the learned automaton is drawn from different classes of finite automata. One of our dichotomy results closes a gap for the general DFA consistency problem, as here, for fixed alphabet size, the NP-hardness proofs in the literature have some issues. Interestingly, our NP-hardness results hold even for severely restricted classes of automata, such as partially-ordered automata and permutation automata. On the other hand, we provide parameterized algorithms for several combinations of parameters and show that most of them are optimal under the exponential time hypothesis.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Also in [2] Mealy automata instead of DFAs are considered.
- 2.
Given a Boolean formula in conjunctive normal form where all clauses have exactly three literals (this form is called 3CNF) and all literals are positive. Is there a variable assignment such that exactly one literal per clause evaluates to true?.
- 3.
In general \(V_0, V_1, V_2\) is not a partition of V since some of the sets might be empty if G is 1- or 2-colorable.
References
Abdulla, P.A., Collomb-Annichini, A., Bouajjani, A., Jonsson, B.: Using forward reachability analysis for verification of lossy channel systems. Formal Methods Syst. Des. 25(1), 39–65 (2004)
Angluin, D.: On the complexity of minimum inference of regular sets. Inf. Control 39(3), 337–350 (1978)
Angluin, D.: Inference of reversible languages. J. ACM 29(3), 741–765 (1982)
Bouhmala, N.: A multilevel learning automata for MAX-SAT. Int. J. Mach. Learn. Cybern. 6(6), 911–921 (2015)
Brzozowski, J.A., Fich, F.E.: Languages of R-trivial monoids. J. Comput. Syst. Sci. 20(1), 32–49 (1980)
Clifford, A.H., Preston, G.B.: The Algebraic Theory of Semigroups, Volume II, vol. 2. American Mathematical Soc., Providence (1967)
Coste, F., Kerbellec, G.: Learning automata on protein sequences. In: JOBIM, pp. 199–210 (2006)
Cygan, M., et al.: Parameterized Algorithms. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-21275-3_15
Downey, R.G., Fellows, M.R.: Fundamentals of Parameterized Complexity, vol. 4. Springer, London (2013). https://doi.org/10.1007/978-1-4471-5559-1
Fernau, H.: Personal communication (2021)
Fernau, H.: Algorithms for learning regular expressions from positive data. Inf. Comput. 207(4), 521–541 (2009)
Fernau, H., Heggernes, P., Villanger, Y.: A multi-parameter analysis of hard problems on deterministic finite automata. J. Comput. Syst. Sci. 81(4), 747–765 (2015)
Fernau, H., Krebs, A.: Problems on finite automata and the exponential time hypothesis. Algorithms 10(1), 24 (2017)
Gold, E.M.: Language identification in the limit. Inf. Control 10(5), 447–474 (1967)
Gold, E.M.: Complexity of automaton identification from given data. Inf. Control 37(3), 302–320 (1978)
Groce, A., Peled, D., Yannakakis, M.: Adaptive model checking. In: Katoen, J.-P., Stevens, P. (eds.) TACAS 2002. LNCS, vol. 2280, pp. 357–370. Springer, Heidelberg (2002). https://doi.org/10.1007/3-540-46002-0_25
Gruber, H., Holzer, M.: Finite automata, digraph connectivity, and regular expression size. In: Aceto, L., Damgård, I., Goldberg, L.A., Halldórsson, M.M., Ingólfsdóttir, A., Walukiewicz, I. (eds.) ICALP 2008. LNCS, vol. 5126, pp. 39–50. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-70583-3_4
Guo, H., Wang, S., Fan, J., Li, S.: Learning automata based incremental learning method for deep neural networks. IEEE Access 7, 41164–41171 (2019)
Hasanzadeh-Mofrad, M., Rezvanian, A.: Learning automata clustering. J. Comput. Sci. 24, 379–388 (2018)
De la Higuera, C.: Grammatical Inference: Learning Automata and Grammars. Cambridge University Press, Cambridge (2010)
Impagliazzo, R., Paturi, R.: On the complexity of k-SAT. J. Comput. Syst. Sci. 62(2), 367–375 (2001)
Impagliazzo, R., Paturi, R., Zane, F.: Which problems have strongly exponential complexity? J. Comput. Syst. Sci. 63(4), 512–530 (2001)
Jirásková, G., Masopust, T.: On the state and computational complexity of the reverse of acyclic minimal DFAs. In: Moreira, N., Reis, R. (eds.) CIAA 2012. LNCS, vol. 7381, pp. 229–239. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-31606-7_20
Klíma, O., Polák, L.: Alternative automata characterization of piecewise testable languages. In: Béal, M.-P., Carton, O. (eds.) DLT 2013. LNCS, vol. 7907, pp. 289–300. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-38771-5_26
Lokshtanov, D., Marx, D., Saurabh, S., et al.: Lower bounds based on the exponential time hypothesis. Bull. EATCS 3(105), 41–71 (2013)
Mao, H., Chen, Y., Jaeger, M., Nielsen, T.D., Larsen, K.G., Nielsen, B.: Learning deterministic probabilistic automata from a model checking perspective. Mach. Learn. 105(2), 255–299 (2016). https://doi.org/10.1007/s10994-016-5565-9
Martens, W., Neven, F., Schwentick, T.: Complexity of decision problems for XML schemas and chain regular expressions. SIAM J. Comput. 39(4), 1486–1530 (2009)
Mayr, F., Yovine, S.: Regular inference on artificial neural networks. In: Holzinger, A., Kieseberg, P., Tjoa, A.M., Weippl, E. (eds.) CD-MAKE 2018. LNCS, vol. 11015, pp. 350–369. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-99740-7_25
Meybodi, M.R., Beigy, H.: New learning automata based algorithms for adaptation of backpropagation algorithm parameters. Int. J. Neural Syst. 12(01), 45–67 (2002)
Mount, D.W., Mount, D.W.: Bioinformatics: Sequence and Genome Analysis, vol. 1. Cold Spring Harbor Laboratory Press, Cold Spring Harbor, NY (2001)
Najim, K., Pibouleau, L., Le Lann, M.: Optimization technique based on learning automata. J. Optim. Theory Appl. 64(2), 331–347 (1990)
Najim, K., Poznyak, A.S.: Learning Automata: Theory and Applications. Elsevier, Amsterdam (2014)
Nowé, A., Verbeeck, K., Peeters, M.: Learning automata as a basis for multi agent reinforcement learning. In: Tuyls, K., Hoen, P.J., Verbeeck, K., Sen, S. (eds.) LAMAS 2005. LNCS (LNAI), vol. 3898, pp. 71–85. Springer, Heidelberg (2006). https://doi.org/10.1007/11691839_3
Parekh, R., Honavar, V.: Learning DFA from simple examples. Mach. Learn. 44(1), 9–35 (2001)
Pin, J.-E.: On reversible automata. In: Simon, I. (ed.) LATIN 1992. LNCS, vol. 583, pp. 401–416. Springer, Heidelberg (1992). https://doi.org/10.1007/BFb0023844
Pitt, L.: Inductive inference, DFAs, and computational complexity. In: Jantke, K.P. (ed.) AII 1989. LNCS, vol. 397, pp. 18–44. Springer, Heidelberg (1989). https://doi.org/10.1007/3-540-51734-0_50
Pitt, L., Warmuth, M.K.: The minimum consistent DFA problem cannot be approximated within any polynomial. J. ACM 40(1), 95–142 (1993)
Ramadge, P.J., Wonham, W.M.: Supervisory control of a class of discrete event processes. SIAM J. Control. Optim. 25(1), 206–230 (1987)
Rezvanian, A., Saghiri, A.M., Vahidipour, S.M., Esnaashari, M., Meybodi, M.R.: Recent Advances in Learning Automata. SCI, vol. 754. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-72428-7
Ryzhikov, A.: Synchronization problems in automata without non-trivial cycles. Theoret. Comput. Sci. 787, 77–88 (2019)
Schaefer, T.J.: The complexity of satisfiability problems. In: Lipton, R.J., Burkhard, W.A., Savitch, W.J., Friedman, E.P., Aho, A.V. (eds.) Proceedings of the 10th Annual ACM Symposium on Theory of Computing, pp. 216–226. ACM (1978)
Schützenberger, M.P.: On finite monoids having only trivial subgroups. Inf. Control 8(2), 190–194 (1965)
Simon, I.: Piecewise testable events. In: Brakhage, H. (ed.) GI-Fachtagung 1975. LNCS, vol. 33, pp. 214–222. Springer, Heidelberg (1975). https://doi.org/10.1007/3-540-07407-4_23
Thierrin, G.: Permutation automata. Mathem. Syst. Theory 2(1), 83–90 (1968)
Yazidi, A., Bouhmala, N., Goodwin, M.: A team of pursuit learning automata for solving deterministic optimization problems. Appl. Intell. 50(9), 2916–2931 (2020)
Acknowledgements
Petra Wolf was supported by DFG project FE 560/9-1, and Mateus de Oliveira Oliveira by the RCN projects 288761 and 326537.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Lingg, J., de Oliveira Oliveira, M., Wolf, P. (2022). Learning from Positive and Negative Examples: Dichotomies and Parameterized Algorithms. In: Bazgan, C., Fernau, H. (eds) Combinatorial Algorithms. IWOCA 2022. Lecture Notes in Computer Science, vol 13270. Springer, Cham. https://doi.org/10.1007/978-3-031-06678-8_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-06678-8_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-06677-1
Online ISBN: 978-3-031-06678-8
eBook Packages: Computer ScienceComputer Science (R0)