Abstract
In this paper, the authors consider interworking between statistical procedures for recoveringthe distribution of random parameters from observations and stochastic programmingtechniques, in particular stochastic gradient (quasigradient) methods. The proposed problemformulation is based upon a class of statistical models known as Bayesian nets. The reasonfor the latter choice is that Bayesian nets are powerful and general statistical models emergedrecently within the more general framework of Bayesian statistics, which is specificallydesigned for cases when the vector of random parameters can have considerable dimensionandyor it is difficult to come up with traditional parametric models of the joint distribution ofrandom parameters. We define the optimization problem on a Bayesian net. For the solutionof this problem, we develop algorithms for sensitivity analysis of such a net and presentcombined optimization and sampling techniques.
Similar content being viewed by others
References
A. Frigessi, P. Di Stefano, C.R. Hwang and S.J. Sheu, Convergence rates of the Gibbs sampler, the Metropolis algorithm and other single-site updating dynamics, J.R. Statist. Soc. B55(1993)205–219.
A. Gaivoronski, M. Morassutto, S. Silani and F. Stella, Numerical techniques for solving estimation problems on robust Bayesian nets, in: Proc. of the 2nd Int. Workshop on Bayesian Robustness, 1996.
J.R. Birge and R.J-B. Wets, Computing bounds for stochastic programming problems by means of a generalized moment problem, Mathematics of Operations Research 12(1987)149–162.
C. Berzuini, Modeling temporal processes via belief networks and Petri nets, with application to expert systems, Annals of Mathematics and Artificial Intelligence 2(1990)39–64.
C. Berzuini, R. Bellazzi, S. Quaglini and D.J. Spiegelhalter, Bayesian network for patient monitoring, Artificial Intelligence in Medicine 4(1992)243–260.
M. Dall'Aglio and G. Salinetti, Bayesian robustnesss, moment problem and semi-finite linear programming, manuscript, 1994.
M. Dempster (ed.), Stochastic Programming, Academic Press, London, 1980.
D.J. Spiegelhalter, A.P. Dawid, S.L. Lauritzen and R.G. Cowell, Bayesian analysis in expert systems, Statistical Science, 1993.
J. Dupačová, On statistical sensitivity analysis in stochastic programming, Annals of Operations Research 30(1991)199–214.
Yu. Ermoliev, Methods of Stochastic Programming, Nauka, Moscow, 1976 (in Russian).
Yu. Ermoliev and R.J-B. Wets (eds.), Numerical Techniques for Stochastic Optimization, Springer, Berlin, 1988.
F. Stella, Problemi di ottimizzaxione su reti Bayesiane, Ph.D. Thesis, Computational Mathematics and Operations Research, 1995.
A.A. Gaivoronski, On nonstationary stochastic optimization problems, Cybernetics 14(1978).
A.A. Gaivoronski, Implementation of stochastic quasigradient methods, in: Numerical Techniques for Stochastic Optimization, eds. Yu. Ermoliev and R.J-B. Wets, Springer, Berlin, 1988.
A.A. Gaivoronki, E. Messina and A. Sciomachen, A statistical generalized programming algorithm for stochastic optimization problems, Annals of Operations Research 58(1995)297–321.
P.W. Glynn and D.L. Iglehart, Importance sampling for stochastic simulations, Management Science 35(1989)1367–1392.
J.L. Higle and S. Sen, Stochastic decomposition: An algorithm for stage linear programs with recouse, Mathematics of Operations Research 16(1991)650–669.
J.H. Kim and J. Pearl, A computational model for causal and diagnostic reasoning in inference engines, in: 8th International Joint Conference on AI Proceedings, 1983.
J. Pearl, Probabilistic Reasoning in Intelligent Systems, Morgan Kaufmann, 1988.
P. Kall, Stochastic Linear Programming, Springer, Berlin, 1976.
A.J. King, Asymptotic behavior of solutions in stochastic optimization: Nonsmooth analysis and the derivation of non-normal limit distribution, Ph.D. Thesis, University of Washington, 1986.
K. Marti and E. Fuchs, Computation of descent directions and efficient points in stochastic optimization problems without using derivatives, Mathematical Programming Study 28(1986)132–156.
M. Henrion, J.S. Breese and E.J. Horvitz, Decision analysis and expert systems, AI Magazine (1991).
M. Peot and D. Shachter, Simulation approaches to general probabilistic inference on belief networks, Uncertainty in AI 5, 1990.
J.M. Mulvey and H. Vladimirou, Applying the progressive hedging algorithm to stochastic generalized networks, Annals of Operations Research 31(1991)399–424.
S.S. Nielsen and S.A. Zenios, Solving multistage stochastic network programs, Technical Report 92-08-04, Decision Sciences Department, University of Pennsylvania, Philadelphia, 1992.
P. Barone and A. Frigessi, Improving stochastic relaxation for Gaussian random fields, Prob. Eng. Inf. Sci. 4(1990)369–389.
G. Pflug, On-line optimization of simulated Markov processes, Mathematics of Operations Research 15(1990)381–395.
A. Prékopa, Contributions to the theory of stochastic programming, Mathematical Programming 4(1973)202–221.
R.D. Schachter, Probabilistic inference, Operations Research 38(1988).
R.E. Fung and K. Chang, Weighting and integrating evidence for stochastic simulation in Bayesian networks, Uncertainty in AI 5, 1990.
R.E. Neapolitan, Probabilistic Reasoning in Expert Systems, Wiley, 1990.
S.M. Robinson, Extended scenario analysis, Annals of Operations Research 31(1991)385–398.
R.T. Rockafellar and R.J-B. Wets, A Lagrangian finite generation technique for solving linearquadratic problems in stochastic programming, Mathematical Programming Study 28(1986)63–93.
W. Römisch and R. Schultz, Distribution sensitivity for certain classes of chance-constrained models with application to power dispatch, Journal of Optimization Theory and Applications 71(1991) 569–588.
R. Rubinstein, Sensitivity analysis and performance extrapolation for computer simulation models, Operations Research 37(1989)72–81.
S. Geman and D. Geman, Stochastic relaxation, Gibbs distribution, and the Bayesian restoration of images, IEEE Transactions on Pattern Analysis and Machine Intelligence 6(1984)721–742.
A. Shapiro, Asymptotic properties of statistical estimators in stochastic programming, Annals of Statistics 17(1989)841–858.
T. Verma and J. Pearl, Causal networks: Semantic and expressiveness, in: Uncertainty in Artificial Intelligence, Vol. 4, eds. R. Shachter, T.S. Levitt and L.N. Kanal, Elsevier Science, 1990, pp. 69–76.
S.W. Wallace and R.J-B. Wets, Preprocessing in stochastic programming: The case of capacitated networks, ORSA Journal on Computing 7(1995)44–62.
R.J-B. Wets, Stochastic programming: Solution techniques and approximation schemes, in: Mathematical Programming: The State of the Art, eds. A. Bachem, M. Grötschel and B. Korte, Springer, Berlin, 1982
Rights and permissions
About this article
Cite this article
Gaivoronski, A., Stella, F. Stochastic optimization with structured distributions:The case of Bayesian nets. Annals of Operations Research 81, 189–212 (1998). https://doi.org/10.1023/A:1018948905888
Issue Date:
DOI: https://doi.org/10.1023/A:1018948905888