Symmetric measures via moments
Koloydenko, Alexey
Bernoulli, Tome 14 (2008) no. 1, p. 362-390 / Harvested from Project Euclid
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.
Publié le : 2008-05-15
Classification:  algebraic statistics,  determinate measures,  finite groups,  linear transformations,  log-linear models,  maximum entropy,  polynomial invariants,  symmetry,  toric models
@article{1208872109,
     author = {Koloydenko, Alexey},
     title = {Symmetric measures via moments},
     journal = {Bernoulli},
     volume = {14},
     number = {1},
     year = {2008},
     pages = { 362-390},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1208872109}
}
Koloydenko, Alexey. Symmetric measures via moments. Bernoulli, Tome 14 (2008) no. 1, pp.  362-390. http://gdmltest.u-ga.fr/item/1208872109/