Abstract
We have recently developed new maximum entropy (MaxEnt) and Bayesian methods for the analysis of flow networks, including pipe flow, electrical and transportation networks. Both methods of inference update a prior probability density function (pdf) with new information, in the form of data or constraints, to obtain a posterior pdf for the system. We here examine the effects of non-Gaussian prior pdfs, including truncated normal and beta distributions, both analytically and by the use of numerical examples, to explore the differences and similarities between the MaxEnt and Bayesian formulations. We also examine ‘soft constraints’ imposed within the prior.
Keywords
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Boltzmann, L.: Über die Beziehung zwischen dem zweiten Hauptsatz der mechanischen Wärmetheorie und der Wahrscheinlichkeitsrechnung respektive den Sätzen über das Wärmegleichgewicht (On the Relationship between the Second Fundamental Theorem of the Mechanical Theory of H. Wiener Berichte 2(76), 373–435 (1877)
Caticha, A.: Relative entropy and inductive inference. Bayesian Inference Maximum Entropy Methods Sci. Eng. 707, 75–96 (2004). https://doi.org/10.1063/1.1751358
Caticha, A., Giffin, A.: Updating probabilities. In: AIP Conference Proceedings, vol. 872, pp. 31–42. AIP (2006). https://doi.org/10.1063/1.2423258
Giffin, A.: Maximum entropy: the universal method for inference. Ph.D. thesis, University at Albany, State University of New York (2008)
Giffin, A., Caticha, A.: Updating probabilities with data and moments. In: AIP Conference Proceedings, vol. 954, pp. 74–84. AIP (2007). https://doi.org/10.1063/1.2821302
Hennig, P., Kiefel, M.: Quasi-Newton methods: a new direction. In: Proceedings of the 29th International Conference on Machine Learning (ICML-12), vol. 29, pp. 25–32 (2012)
Hennig, P., Kiefel, M.: Quasi-Newton methods: a new direction. J. Mach. Learn. Res. 14, 843–865 (2013)
Jaynes, E.T.: Information theory and statistical mechanics. Phys. Rev. 106(4), 620–630 (1957)
Jaynes, E.T.: Prior probabilities. IEEE Trans. Syst. Sci. Cybern. 4(3), 227–241 (1968). https://doi.org/10.1109/TSSC.1968.300117
Jaynes, E.T.: Probability Theory: The Logic of Science. Cambridge University Press, Cambridge (2003)
Kapur, J.N., Kesavan, H.K.: Entropy Optimization Principles with Applications. Academic Press, Boston (1992)
Kullback, S., Leibler, R.A.: On information and sufficiency. Ann. Math. Stat. 22(1), 79–86 (1951). https://doi.org/10.2307/2236703
Manjunath, B.G., Stefan, W.: Moments calculation for the double truncated multivariate normal density. SSRN Electron. J. 1963, 1–11 (2009). https://doi.org/10.2139/ssrn.1472153
Niven, R.K.: Combinatorial entropies and statistics. Eur. Phys. J. B 70(1), 49–63 (2009). https://doi.org/10.1140/epjb/e2009-00168-5
Shannon, C.E.: A mathematical theory of communication. Bell Syst. Tech. J. 27(4), 623–656 (1948). https://doi.org/10.1002/j.1538-7305.1948.tb00917.x
Sharp, K., Matschinsky, F.: Translation of Ludwig Boltzmann’s Paper On the Relationship between the Second Fundamental Theorem of the Mechanical Theory of Heat and Probability Calculations Regarding the Conditions for Thermal Equilibrium Sitzungberichte der Kaiserlichen Akademie d. Entropy 17(4), 1971–2009 (2015). https://doi.org/10.3390/e17041971
Shore, J., Johnson, R.: Axiomatic derivation of the principle of maximum entropy and the principle of minimum cross-entropy. IEEE Trans. Inf. Theory 26(1), 26–37 (1980). https://doi.org/10.1109/TIT.1980.1056144
Waldrip, S., Niven, R.: Comparison between Bayesian and maximum entropy analyses of flow networks. Entropy 19(2), 58 (2017). https://doi.org/10.3390/e19020058
Waldrip, S.H.: Probabilistic analysis of flow networks using the maximum entropy method. Ph.D. thesis, The University of New South Wales, Canberra Australia (2017)
Waldrip, S.H., Niven, R.K.: Maximum entropy derivation of Quasi-Newton methods. SIAM J. Optim. 26(4), 2495–2511 (2016). https://doi.org/10.1137/15M1027668
Williams, P.M.: Bayesian conditionalisation and the principle of minimum information. Br. J. Philos. Sci. 31(2), 131–144 (1980)
Acknowledgements
This project acknowledges funding support from the Australian Research Council Discovery Projects Grant DP140104402, Go8/DAAD Australia-Germany Joint Research Cooperation Scheme RG123832 and the French Agence Nationale de la Recherche Chair of Excellence (TUCOROM) and the Institute Prime, Poitiers, France.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Employee of the Crown
About this paper
Cite this paper
Waldrip, S.H., Niven, R.K. (2018). Bayesian and Maximum Entropy Analyses of Flow Networks with Non-Gaussian Priors and Soft Constraints. In: Polpo, A., Stern, J., Louzada, F., Izbicki, R., Takada, H. (eds) Bayesian Inference and Maximum Entropy Methods in Science and Engineering. maxent 2017. Springer Proceedings in Mathematics & Statistics, vol 239. Springer, Cham. https://doi.org/10.1007/978-3-319-91143-4_27
Download citation
DOI: https://doi.org/10.1007/978-3-319-91143-4_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-91142-7
Online ISBN: 978-3-319-91143-4
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)