Abstract
We formulate an optimization stochastic algorithm convergence theorem, of Solis and Wets type, and we show several instances of its application to concrete algorithms. In this convergence theorem the algorithm is a sequence of random variables and, in order to describe the increasing flow of information associated to this sequence we define a filtration – or flow of \(\sigma \)-algebras – on the probability space, depending on the sequence of random variables and on the function being optimized. We compare the flow of information of two convergent algorithms by comparing the associated filtrations by means of the Cotter distance of \(\sigma \)-algebras. The main result is that two convergent optimization algorithms have the same information content if both their limit minimization functions generate the full \(\sigma \)-algebra of the probability space.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Appel, M.J., LaBarre, R., Radulović, D.: On accelerated random search. SIAM J. Optim. 14(3), 708–731 (2003). (Electronic)
Artstein, Z.: Compact convergence of \(\sigma \)-fields and relaxed conditional expectation. Probab. Theory Relat. Fields 120(3), 369–394 (2001)
Barty, K.: Contributions à la discrétisation des contraintes de mesurabilité pour les problèmes d’optimisation stochastique. Ph.D. thesis, École Nationale des Ponts et Chaussées, Paris, France, June 2004
Billingsley, P.: Probability and Measure. Wiley Series in Probability and Mathematical Statistics, 3rd edn. Wiley, New York (1995)
Boylan, E.S.: Equiconvergence of martingales. Ann. Math. Stat. 42, 552–559 (1971)
Costa, A., Jones, O.D., Kroese, D.: Convergence properties of the cross-entropy method for discrete optimization. Oper. Res. Lett. 35(5), 573–580 (2007)
Cotter, K.D.: Similarity of information and behavior with a pointwise convergence topology. J. Math. Econ. 15(1), 25–38 (1986)
Cotter, K.D.: Convergence of information, random variables and noise. J. Math. Econ. 16(1), 39–51 (1987)
de Boer, P.-T., Kroese, D.P., Mannor, S., Rubinstein, R.Y.: A tutorial on the cross-entropy method. Ann. Oper. Res. 134, 19–67 (2005)
de Carvalho, M.: Confidence intervals for the minimum of a function using extreme value statistics. Int. J. Math. Modell. Numer. Optim. 2(9), 288–296 (2011)
de Carvalho, M.: A generalization of the Solis and Wets method. J. Stat. Plann. Inference 142(3), 633–644 (2012)
Esquível, M.L.: A conditional Gaussian martingale algorithm for global optimization. In: Gavrilova, M., et al. (eds.) ICCSA 2006, Part III. LNCS, vol. 3982, pp. 841–851. Springer, Heidelberg (2006). https://doi.org/10.1007/11751595_89
Komisarski, A.: Distances between \(\sigma \)-fields on a probability space. J. Theoret. Probab. 21(4), 812–823 (2008)
Kudō, H.: A note on the strong convergence of \(\sigma \)-algebras. Ann. Probab. 2(1), 76–83 (1974)
Mexia, J.T., Pereira, D., Baeta, J.: \(L_2\) environmental indexes. Listy Biom. 36(2), 137–143 (1999)
Neveu, J.: Bases mathématiques du calcul des probabilités. Masson et Cie, Éditeurs, Paris (1964)
Neveu, J.: Mathematical Foundations of the Calculus of Probability. Translated by Amiel Feinstein. Holden-Day Inc., San Francisco (1965)
Neveu, J.: Note on the tightness of the metric on the set of complete sub \(\sigma \)-algebras of a probability space. Ann. Math. Stat. 43, 1369–1371 (1972)
Piccinini, L.: Convergence of nonmonotone sequence of sub-\(\sigma \)-fields and convergence of associated subspaces \(L^p(\cal{B}_n) (p\in [1,+\infty ])\). J. Math. Anal. Appl. 225(1), 73–90 (1998)
Pereira, D.G., Mexia, J.T.: Comparing double minimization and zigzag algorithms in joint regression analysis: the complete case. J. Stat. Comput. Simul. 80(1–2), 133–141 (2010)
Peng, J., Shi, D.: Improvement of pure random search in global optimization. J. Shanghai Univ. 4(2), 92–95 (2000)
Rubinstein, R.Y., Kroese, D.P.: The Cross-Entropy Method. Information Science and Statistics, Springer, New York (2004). https://doi.org/10.1007/978-1-4757-4321-0. A Unified Approach to Combinatorial Optimization, Monte-Carlo Simulation, and Machine Learning
Rubinstein, R.Y., Kroese, D.P.: Simulation and the Monte Carlo Method. Wiley Series in Probability and Statistics, 2nd edn. Wiley-Interscience, Hoboken (2008)
Rogge, L.: Uniform inequalities for conditional expectations. Ann. Probab. 2, 486–489 (1974)
Raphael, B., Smith, I.F.C.: A direct stochastic algorithm for global search. Appl. Math. Comput. 146(2–3), 729–758 (2003)
Stephens, C.P., Baritompa, W.: Global optimization requires global information. J. Optim. Theory Appl. 96(3), 575–588 (1998)
Shi, D., Peng, J.: A new theoretical framework for analyzing stochastic global optimization algorithms. J. Shanghai Univ. 3(3), 175–180 (1999)
Spall, J.C.: Introduction to Stochastic Search and Optimization. Wiley-Interscience Series in Discrete Mathematics and Optimization. Wiley-Interscience, Hoboken (2003). Estimation, Simulation, and Control
Spall, J.C.: Stochastic optimization. In: Handbook of Computational Statistics, pp. 169–197. Springer, Berlin (2004)
Solis, F.J., Wets, R.J.-B.: Minimization by random search techniques. Math. Oper. Res. 6(1), 19–30 (1981)
Vidmar, M.: A couple of remarks on the convergence of \(\sigma \)-fields on probability spaces. Statist. Probab. Lett. 134, 86–92 (2018)
Van Zandt, T.: The Hausdorff metric of \(\sigma \)-fields and the value of information. Ann. Probab. 21(1), 161–167 (1993)
Wang, X.: Convergence rate of conditional expectations. Sci. Math. Jpn. 53(1), 83–87 (2001)
Yin, G.: Rates of convergence for a class of global stochastic optimization algorithms. SIAM J. Optim. 10(1), 99–120 (1999). (Electronic)
Zabinsky, Z.B.: Stochastic Adaptive Search for Global Optimization. Nonconvex Optimization and its Applications, vol. 72. Kluwer Academic Publishers, Boston (2003)
Acknowledgements
This work was partially supported, for the first and fourth authors, through the project UID/MAT/00297/2020 of the Centro de Matemática e Aplicações, financed by the Fundação para a Ciência e a Tecnologia (Portuguese Foundation for Science and Technology) and, for the third author, through RFBR (Grant n. 19-01-00451).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
A Appendix
A Appendix
Deduction of Formula (2). Let \( \lambda _x\) denote the Lebesgue measure over \(\mathcal {D}\) applied to the set defined by the variable x.
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Esquível, M.L., Machado, N., Krasii, N.P., Mota, P.P. (2021). On the Information Content of Some Stochastic Algorithms. In: Shiryaev, A.N., Samouylov, K.E., Kozyrev, D.V. (eds) Recent Developments in Stochastic Methods and Applications. ICSM-5 2020. Springer Proceedings in Mathematics & Statistics, vol 371. Springer, Cham. https://doi.org/10.1007/978-3-030-83266-7_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-83266-7_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-83265-0
Online ISBN: 978-3-030-83266-7
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)