• Bernoulli
  • Volume 14, Number 2 (2008), 362-390.

Symmetric measures via moments

Alexey Koloydenko

Full-text: Open access


Algebraic tools in statistics have recently been receiving special attention and a number of interactions between algebraic geometry and computational statistics have been rapidly developing. This paper presents another such connection, namely, one between probabilistic models invariant under a finite group of (non-singular) linear transformations and polynomials invariant under the same group. Two specific aspects of the connection are discussed: generalization of the (uniqueness part of the multivariate) problem of moments and log-linear, or toric, modeling by expansion of invariant terms. A distribution of minuscule subimages extracted from a large database of natural images is analyzed to illustrate the above concepts.

Article information

Bernoulli Volume 14, Number 2 (2008), 362-390.

First available in Project Euclid: 22 April 2008

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

algebraic statistics determinate measures finite groups linear transformations log-linear models maximum entropy polynomial invariants symmetry toric models


Koloydenko, Alexey. Symmetric measures via moments. Bernoulli 14 (2008), no. 2, 362--390. doi:10.3150/07-BEJ6144.

Export citation


  • [1] Barron, A.R. and Sheu, C.-H. (1991). Approximation of density functions by sequences of exponential families. Ann. Statist. 19 1347–1369.
  • [2] Berg, C. (1996). Moment problems and polynomial approximation. Ann. Fac. Sci. Toulouse Math. (6) 9–32.
  • [3] Billingsley, P. (1995). Probability and Measure, 3rd ed. New York: Wiley.
  • [4] Computational Algebra Group School of Mathematics & Statistics University of Sydney (2003). The Magma Computational Algebra System. Release Notes V2.10. Computational Algebra Group School of Mathematics & Statistics University of Sydney. Available at
  • [5] Cover, T.M. and Thomas, J.A. (1991). Elements of Information Theory. New York: Wiley.
  • [6] Cox, D., Little, J. and O’Shea, D. (1997). Ideals, Varieties, and Algorithms, 2nd ed. New York: Springer.
  • [7] Csiszár, I. (1975). I-divergence geometry of probability distributions and minimization problems. Ann. Probab. 3 146–158.
  • [8] Csiszár, I. (1991). Why least squares and maximum entropy? An axiomatic approach to inference for linear inverse problems. Ann. Statist. 19 2032–2066.
  • [9] de Jeu, M. (2003). Determinate multidimensional measures, the extended Carleman theorem and quasi-analytic weights. Ann. Probab. 31 1205–1227.
  • [10] Della Pietra, S., Della Pietra, V. and Lafferty, J. (1997). Inducing features of random fields. IEEE Trans. PAMI 19 45–47.
  • [11] Derksen, H. and Kemper, G. (2002). Computational Invariant Theory. Berlin: Springer.
  • [12] Drton, M. and Sullivant, S. (2007). Algebraic statistical models. Statist. Sinica 14 1273–1297.
  • [13] Dummit, D.S. and Foote, R.M. (1991). Abstract Algebra. Englewood Cliffs, NJ: Prentice Hall Inc.
  • [14] Durrett, R. (1996). Probability: Theory and Examples, 2nd ed. Belmont, CA: Duxbury Press.
  • [15] Dykstra, R.L. and Lemke, J.H. (1988). Duality of I projections and maximum likelihood estimation for log-linear models under cone constraints. J. Amer. Statist. Assoc. 83 546–554.
  • [16] Fleuret, F. and Geman, D. (2001). Coarse-to-fine face detection. Int. J. Comput. Vision 41 85–107.
  • [17] Fogarty, J. (2001). On Noether’s bound for polynomial invariants of a finite group. Electron. Res. Announc. Amer. Math. Soc. 7 5–7.
  • [18] Geiger, D., Meek, C. and Sturmfels, B. (2006). On the toric algebra of graphical models. Ann. Statist. 34 1463–1492.
  • [19] Geman, D. and Koloydenko, A. (1999). Invariant statistics and coding of natural microimages. In IEEE Workshop Statist. Comput. Theories of Vision (S. Zhu, ed.). Published on web at
  • [20] Grayson, D. and Stillman, M. Macaulay 2, a software system for research in algebraic geometry. Available at
  • [21] Hastie, T., Tibshirani, R. and Friedman, J. (2001). The Elements of Statistical Learning. New York: Springer.
  • [22] Hateren, J.H.V. and Schaaf, A.V.D. (1998). Independent component filters of natural images compared with simple cells in primary visual cortex. Proc. R. Soc. Lond. B 265 359–366.
  • [23] Heiler, M. and Schnörr, C. (2003). Natural image statistics for natural image segmentation. In Proc. of the 9th ICCV 1259–1266. IEEE Computer Society.
  • [24] Huang, J. and Mumford, D. (1999). Statistics of natural images and models. In Proc. of CVPR 541–547. IEEE Computer Society.
  • [25] Ishwar, P. and Moulin, P. (2005). On the existence and characterization of the maxent distribution under general moment inequality constraints. IEEE Trans. Inform. Theory 51 3322–3333.
  • [26] Junk, M. (2000). Maximum entropy for reduced moment problems. Math. Models Methods Appl. Sci. 10 1001–1025.
  • [27] Jupp, P.E. and Mardia, K.V. (1983). A note on the maximum-entropy principle. Scand. J. Statist. 10 45–47.
  • [28] Keich, U. (1999). Krein’s strings, the symmetric moment problem, and extending a real positive definite function. Comm. Pure Appl. Math. 52 1315–1334.
  • [29] Kemper, G. INVAR. A Maple package for invariant theory of finite groups. Available from
  • [30] Koloydenko, A. (2000). Modeling natural microimage statistics. Ph.D. thesis, Univ. Massachusetts Amherst. Available at
  • [31] Koloydenko, A. (2006). Symmetric measures via moments. Technical Report 06-07, School of Mathematical Sciences, Nottingham Univ., UK. Available at
  • [32] Koloydenko, A. and Geman, D. (2006). Ordinal coding of image microstructure. In Int. Conf. Image Proc., Comput. Vision, Pattern Recogn. (H.R. Arabnia, ed.) 613–620. CSREA Press.
  • [33] Lauritzen, S.L. (1996). Graphical Models. New York: The Clarendon Press Oxford University Press.
  • [34] Lee, A.B., Pedersen, K.S. and Mumford, D. (2003). The nonlinear statistics of high-contrast patches in natural images. Internat. Comput. Vision 54 83–103. Available at
  • [35] Lehmann, E.L. (1997). Testing Statistical Hypotheses, 2nd ed. New York: Springer.
  • [36] McCullagh, P. (2002). What is a statistical model? (with discussion). Ann. Statist. 30 1225–1310.
  • [37] Mumford, D. and Gidas, B. (2001). Stochastic models for generic images. Quart. Appl. Math. 59 85–111.
  • [38] Olver, P.J. (1999). Classical Invariant Theory. Cambridge Univ. Press.
  • [39] Pachter, L. and Sturmfels, B., eds. (2005). Algebraic Statistics for Computational Biology. Cambridge Univ. Press.
  • [40] Pedersen, K. (2003). Statistics of natural image geometry. Ph.D. thesis, Dept. Computer Science, Univ. Copenhagen.
  • [41] Pedersen, K. and Lee, A. (2002). Toward a full probability model of edges in natural images. In 7th ECCV 1 (A. Heyden, G. Sparr, M. Nielsen and P. Johansen, eds.) 328–342. Springer.
  • [42] Schervish, M.J. (1995). Theory of Statistics. New York: Springer.
  • [43] Shore, J.E. and Johnson, R.W. (1980). Axiomatic derivation of the principle of maximum entropy and the principle of minimum cross-entropy. IEEE Trans. Inform. Theory 26 26–37.
  • [44] Smith, L. (1995). Polynomial Invariants of Finite Groups. Wellesley, MA: A K Peters Ltd.
  • [45] Stoyanov, J. (2000). Krein condition in probabilistic moment problems. Bernoulli 6 939–949.
  • [46] Sturmfels, B. (1993). Algorithms in Invariant Theory. Vienna: Springer.
  • [47] The GAP Group (2002). GAP – Groups, Algorithms, and Programming, Version 4.3. The GAP Group. Available at
  • [48] Topsøe, F. (2001). Basic concepts, identities and inequalities – the toolkit of information theory. Entropy 3 162–190.
  • [49] Viana, M. (2005). Symmetry studies. Technical Report 027, Eurandom, Eindhoven, The Netherlands. Available at
  • [50] Viola, P. and Jones, M. (2004). Robust real-time object detection. Int. J. Comput. Vision 57 137–154.
  • [51] Zhu, S., Lanterman, A. and Miller, M. (1998). Clutter modeling and performance and analysis in automatic target recognition. In Workshop on Detection Classification of Difficult Targets 477–496. Redstone Arsenal.
  • [52] Zhu, S., Wu, Y. and Mumford, D. (1997). Minimax entropy principle and its application to texture modeling. Neural Computation 9 1627–1660.