Abstract

Existence, uniqueness, and approximations of smooth solutions to team optimization problems with stochastic information structure are investigated. Suboptimal strategies made up of linear combinations of basis functions containing adjustable parameters are considered. Estimates of their accuracies are derived by combining properties of the unknown optimal strategies with tools from nonlinear approximation theory. The estimates are obtained for basis functions corresponding to sinusoids with variable frequencies and phases, Gaussians with variable centers and widths, and sigmoidal ridge functions. The theoretical results are applied to a problem of optimal production in a multidivisional firm, for which numerical simulations are presented.

MSC codes

  1. 90B50
  2. 90B70
  3. 90C15
  4. 90C30
  5. 91A12
  6. 91A35
  7. 91B06
  8. 91B16
  9. 91B38

Keywords

  1. information structure
  2. team utility
  3. infinite-dimensional programming (functional optimization)
  4. approximation schemes
  5. suboptimal solutions
  6. model complexity
  7. curse of dimensionality
  8. optimal production in a firm

Get full access to this article

View all available purchase options and get full access to this article.

References

1.
R. A. Adams and J. J. F. Fournier, Sobolev Spaces, Academic Press, Amsterdam, 2003.
2.
H. Attouch, G. Buttazzo, and G. Michaille, Variational Analysis in Sobolev and BV Spaces: Applications to PDEs and Optimization, SIAM, Philadephia, 2005.
3.
Y. Azrieli and E. Lehrer, The value of a stochastic information structure, Games Econom. Behav., 63 (2008), pp. 679–693.
4.
T. Başar and R. Bansal, The Theory of Teams: A Selective Annotated Bibliography, Lecture Notes in Control and Inform. Sci. 119, Springer, Berlin, 1989.
5.
A. R. Barron, Universal approximation bounds for superpositions of a sigmoidal function, IEEE Trans. Inform. Theory, 39 (1993), pp. 930–945.
6.
T. Başar and G. J. Olsder, Dynamic Noncooperative Game Theory, 2nd ed., SIAM, Philadelphia, 1999.
7.
R. Bellman, Dynamic Programming, Princeton University Press, Princeton, NJ, 1957.
8.
L. D. Berkovitz, Convexity and Optimization in ${\mathbb R}^n$, Wiley, New York, 2002.
9.
T. W. S. Chow and S.-Y. Cho, Neural Networks and Computing: Learning Algorithms and Applications, World Scientific, River Edge, NJ, 2007.
10.
T. M. Cover and J. A. Thomas, Elements of Information Theory, Wiley, New York, 2006.
11.
G. Cybenko, Approximation by superpositions of a sigmoidal function, Math. Control Signals Systems, 2 (1989), pp. 303–314.
12.
B. Dacorogna, Introduction to the Calculus of Variations, Imperial College Press, London, 2004.
13.
S. Giulini and M. Sanguineti, On dimension–independent approximation by neural networks and linear approximators, in Proceedings of the International Joint Conference on Neural Networks, 2000, pp. I283–I288.
14.
S. Giulini and M. Sanguineti, Approximation schemes for functional optimization problems, J. Optim. Theory Appl., 140 (2009), pp. 33–54.
15.
G. Gnecco and M. Sanguineti, Approximation error bounds via Rademacher's complexity, Appl. Math. Sci., 2 (2008), pp. 153–176.
16.
G. Gnecco and M. Sanguineti, Suboptimal solutions to dynamic optimization problems via approximations of the policy functions, J. Optim. Theory Appl., 146 (2010), pp. 764–794.
17.
G. Gnecco and M. Sanguineti, Team optimization problems with Lipschitz continuous strategies, Optim. Lett., 5 (2011), pp. 333–346.
18.
B. I. Golubov, Multiple Fourier series and integrals, J. Math. Sci., 24 (1984), pp. 639–673.
19.
J. Hess, Z. Ider, H. Kagiwada, and R. Kalaba, Team decision theory and integral equations, J. Optim. Theory Appl., 22 (1977), pp. 251–264.
20.
Y.-C. Ho and K.-C. Chu, Team decision theory and information structures in optimal control Part I, IEEE Trans. Automat. Control, 17 (1972), pp. 15–22.
21.
L. K. Jones, Constructive approximation for neural networks by sigmoid functions, Proc. IEEE, 78 (1990), pp. 1586–1589.
22.
P. C. Kainen, V. Kůrková, and M. Sanguineti, Dependence of computational models on input dimension: Tractability of approximation and optimization tasks, IEEE Trans. Inform. Theory, 58 (2012), pp. 1203–1214.
23.
L. Kantorovich and G. Akilov, Functional Analysis in Normed Spaces, Pergamon Press, Oxford, UK, 1964.
24.
K. H. Kim and F. W. Roush, Team Theory, Ellis Horwood Limited, Chichester, UK, 1987.
25.
J. C. Krainak, J. L. Speyer, and S. I. Marcus, Static team problems Part I: Sufficient conditions and the exponential cost criterion, IEEE Trans. Authomat. Control, 27 (1982), pp. 839–848.
26.
A. R. Krommer and C. W. Ueberhuber, Computational Integration, SIAM, Philadelphia, 1998.
27.
V. Kůrková and M. Sanguineti, Comparison of worst case errors in linear and neural network approximation, IEEE Trans. Inform. Theory, 48 (2002), pp. 264–275.
28.
V. Kůrková and M. Sanguineti, Error estimates for approximate optimization by the extended Ritz method, SIAM J. Optim., 18 (2005), pp. 461–487.
29.
V. Kůrková and M. Sanguineti, Approximate minimization of the regularized expected error over kernel models, Math. Oper. Res., 33 (2008), pp. 747–756.
30.
V. Kůrková and M. Sanguineti, Geometric upper bounds on rates of variable-basis approximation, IEEE Trans. Inform. Theory, 54 (2008), pp. 5681–5688.
31.
S. Li and T. Başar, Distributed algorithms for the computation of noncooperative equilibria, Automatica, 23 (1987), pp. 523–533.
32.
Y. Mansour, Lecture Notes for a Course on Computational Game Theory, http://www.cs.tau.ac.il/~mansour/course_games/2006/course_games_05_06.htm (2006).
33.
J. Marschak, Elements for a theory of teams, Manage. Sci., 1 (1955), pp. 127–137.
34.
J. Marschak and R. Radner, Economic Theory of Teams, Yale University Press, New Haven, CT, 1972.
35.
P. Milgrom and R. J. Weber, Distributional strategies for games with incomplete information, Math. Oper. Res., 10 (1985), pp. 619–632.
36.
L. Montrucchio, Lipschitz continuous policy functions for strongly concave optimization problems, J. Math. Econom., 16 (1987), pp. 259–273.
37.
H. Niederreiter, Random Number Generation and Quasi-Monte Carlo Methods, SIAM, Philadelphia, 1992.
38.
N. Nisan, T. Roughgarden, E. Tardos, and V. V. Vazirani, Algorithmic Game Theory, Cambridge University Press, Cambridge, UK, 2007.
39.
J. Nocedal and S. J. Wright, Numerical Optimization, Springer, New York, 2006.
40.
C. H. Papadimitriou and J. N. Tsitsiklis, Intractable problems in control theory, SIAM J. Control Optim., 24 (1986), pp. 639–654.
41.
G. Pisier, Remarques sur un résultat non publié de B. Maurey, in Séminaire d'Analyse Fonctionnelle 1980-81, vol. I, no. 12, École Polytechnique, Centre de Mathématiques, Palaiseau, France, 1981.
42.
T. Poggio and S. Smale, The mathematics of learning: Dealing with data, Not. Amer. Math. Soc., 50 (2003), pp. 537–544.
43.
W. B. Powell, Approximate Dynamic Programming: Solving the Curses of Dimensionality, Wiley, Hoboken, NJ, 2007.
44.
R. Radner, Team decision problems, Ann. Math. Statist., 33 (1962), pp. 857–881.
45.
A. Rantzer, Using Game Theory for Distributed Control Engineering, Technical report ISRN LUTFD2/TFRT–7620–SE, Lund University, Sweden, 2008.
46.
R. T. Rockafellar and R. J.-B. Wets, Variational Analysis, Springer, Berlin, 2004.
47.
W. Rudin, Real and Complex Analysis, McGraw-Hill, Singapore, 1987.
48.
P. Rusmevichientong and B. Van Roy, Decentralized decision-making in a large team with local information, Games Econom. Behav., 43 (2003), pp. 266–295.
49.
Y. Shoham and K. Leyton-Brown, Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations, Cambridge University Press, Cambridge, UK, 2009.
50.
I. Singer, Best Approximation in Normed Linear Spaces by Elements of Linear Subspaces, Springer, Berlin, 1970.
51.
E. M. Stein, Singular Integrals and Differentiability Properties of Functions, Princeton University Press, Princeton, NJ, 1970.
52.
J. N. Tsitsiklis and M. Athans, On the complexity of decentralized decision making and detection problems, IEEE Trans. Automat. Control, 30 (1985), pp. 440–446.
53.
H. S. Witsenhausen, Equivalent stochastic control problems, Math. Control Signals Systems, 1 (1988), pp. 3–11.
54.
Y. Xu, Lecture notes on orthogonal polynomials of several variables, in Advances in the Theory of Special Functions and Orthogonal Polynomials, W. zu Castell, F. Filbir, and B. Forster, eds., Nova Science Publishers, Hauppauge, NY, 2004, pp. 135–188.
55.
T. Zhang, Sequential greedy approximation for certain convex optimization problems, IEEE Trans. Inform. Theory, 49 (2003), pp. 682–691.
56.
T. Zinterhof, High dimensional integration: New weapons fighting the curse of dimensionality, Phys. Part. Nuclei, 5 (2008), pp. 145–149.
57.
T. Zolezzi, Condition numbers and Ritz type methods in unconstrained optimization, Control and Cybernet., 36 (2007), pp. 811–822.
58.
R. Zoppoli, M. Sanguineti, and T. Parisini, Approximating networks and extended Ritz method for the solution of functional optimization problems, J. Optim. Theory Appl., 112 (2002), pp. 403–439.

Information & Authors

Information

Published In

cover image SIAM Journal on Optimization
SIAM Journal on Optimization
Pages: 212 - 243
ISSN (online): 1095-7189

History

Submitted: 26 July 2010
Accepted: 11 November 2011
Published online: 20 March 2012

MSC codes

  1. 90B50
  2. 90B70
  3. 90C15
  4. 90C30
  5. 91A12
  6. 91A35
  7. 91B06
  8. 91B16
  9. 91B38

Keywords

  1. information structure
  2. team utility
  3. infinite-dimensional programming (functional optimization)
  4. approximation schemes
  5. suboptimal solutions
  6. model complexity
  7. curse of dimensionality
  8. optimal production in a firm

Authors

Affiliations

Metrics & Citations

Metrics

Citations

If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.

Cited By

View Options

View options

PDF

View PDF

Media

Figures

Other

Tables

Share

Share

Copy the content Link

Share with email

Email a colleague

Share on social media