Improving Probability Estimation Through Active Probabilistic Model Learning

  • Jingyi Wang
  • Xiaohong Chen
  • Jun Sun
  • Shengchao Qin
Conference paper
First Online:
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10610)

Abstract

It is often necessary to estimate the probability of certain events occurring in a system. For instance, knowing the probability of events triggering a shutdown sequence allows us to estimate the availability of the system. One approach is to run the system multiple times and then construct a probabilistic model to estimate the probability. When the probability of the event to be estimated is low, many system runs are necessary in order to generate an accurate estimation. For complex cyber-physical systems, each system run is costly and time-consuming, and thus it is important to reduce the number of system runs while providing accurate estimation. In this work, we assume that the user can actively tune the initial configuration of the system before the system runs and answer the following research question: how should the user set the initial configuration so that a better estimation can be learned with fewer system runs. The proposed approach has been implemented and evaluated with a set of benchmark models, random generated models, and a real-world water treatment system.

This is a preview of subscription content, log in to check access.

References

  1. 1.
  2. 2.
    Linear programming – Wikipedia, the free encyclopedia (2016). Accessed 24 Nov 2016Google Scholar
  3. 3.
    Mean squared error – Wikipedia, the free encyclopedia (2016). Accessed 7 Dec 2016Google Scholar
  4. 4.
    Angluin, D.: Learning regular sets from queries and counterexamples. Inf. Comput. 75(2), 87–106 (1987)MathSciNetCrossRefMATHGoogle Scholar
  5. 5.
    Baier, C., Katoen, J.-P., et al.: Principles of Model Checking, vol. 26202649. MIT Press, Cambridge (2008)MATHGoogle Scholar
  6. 6.
    Barsotti, F., De Castro, Y., Espinasse, T., Rochet, P.: Estimating the transition matrix of a markov chain observed at random times. Stat. Probab. Lett. 94, 98–105 (2014)MathSciNetCrossRefMATHGoogle Scholar
  7. 7.
    Brinker, K.: Incorporating diversity in active learning with support vector machines. In: Machine Learning, Proceedings of the Twentieth International Conference (ICML 2003), 21–24 August 2003, Washington, DC, USA, pp. 59–66 (2003)Google Scholar
  8. 8.
    Chen, Y., Nielsen, T.D.: Active learning of markov decision processes for system verification. In: 2012 11th International Conference on Machine Learning and Applications (ICMLA), vol. 2, pp. 289–294. IEEE (2012)Google Scholar
  9. 9.
    Cochran, G.: Laplace’s ratio estimator. In: David, H.A. (ed.) Contributions to Survey Sampling and Applied Statistics, pp. 3–10. Academic Press, New York (1978)CrossRefGoogle Scholar
  10. 10.
    Gale, W.A., Sampson, G.: Good-turing frequency estimation without tears*. J. Quant. Linguist. 2(3), 217–237 (1995)CrossRefGoogle Scholar
  11. 11.
    Gurobi Optimization Incorporation: Gurobi optimizer reference manual (2016)Google Scholar
  12. 12.
    Heidelberger, P.: Fast simulation of rare events in queueing and reliability models. ACM Trans. Model. Comput. Simul. (TOMACS) 5(1), 43–85 (1995)CrossRefMATHGoogle Scholar
  13. 13.
    Lesser, K., Oishi, M.: Reachability for partially observable discrete time stochastic hybrid systems. Automatica 50(8), 1989–1998 (2014)MathSciNetCrossRefMATHGoogle Scholar
  14. 14.
    Mao, H., Chen, Y., Jaeger, M., Nielsen, T.D., Larsen, K.G., Nielsen, B.: Learning probabilistic automata for model checking. In: Eighth International Conference on Quantitative Evaluation of Systems (QEST), pp. 111–120. IEEE (2011)Google Scholar
  15. 15.
    McAllester, D.A., Schapire, R.E.: On the convergence rate of good-turing estimators. In: COLT, pp. 1–6 (2000)Google Scholar
  16. 16.
    Moon, T.K.: The expectation-maximization algorithm. IEEE Sig. Proces. Mag. 13(6), 47–60 (1996)CrossRefGoogle Scholar
  17. 17.
    Tabakov, D., Vardi, M.Y.: Experimental evaluation of classical automata constructions. In: Sutcliffe, G., Voronkov, A. (eds.) LPAR 2005. LNCS (LNAI), vol. 3835, pp. 396–411. Springer, Heidelberg (2005). doi: 10.1007/11591191_28 CrossRefGoogle Scholar
  18. 18.
    Wang, J., Sun, J., Qin, S.: Verifying complex systems probabilistically through learning, abstraction and refinement. arXiv preprint arXiv:1610.06371 (2016)
  19. 19.
    Wang, J., Sun, J., Yuan, Q., Pang, J.: Should we learn probabilistic models for model checking? a new approach and an empirical study. In: Huisman, M., Rubin, J. (eds.) FASE 2017. LNCS, vol. 10202, pp. 3–21. Springer, Heidelberg (2017). doi: 10.1007/978-3-662-54494-5_1 CrossRefGoogle Scholar
  20. 20.
    Whittaker, J.A., Thomason, M.G.: A markov chain model for statistical software testing. IEEE Trans. Softw. Eng. 20(10), 812–824 (1994)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Jingyi Wang
    • 1
  • Xiaohong Chen
    • 1
    • 2
  • Jun Sun
    • 1
  • Shengchao Qin
    • 3
  1. 1.Singapore University of Technology and DesignSingaporeSingapore
  2. 2.The University of Illinois at Urbana-ChampaignChampaignUSA
  3. 3.Teesside UniversityMiddlesbroughUK

Personalised recommendations