Finite affine groups: Cycle indices, Hall-Littlewood polynomials, and probabilistic algorithms

The study of asymptotic properties of the conjugacy class of a random element of the finite affine group leads one to define a probability measure on the set of all partitions of all positive integers. Four different probabilistic understandings of this measure are given-three using symmetric function theory and one using Markov chains. This leads to non-trivial enumerative results. Cycle index generating functions are derived and are used to compute the large dimension limiting probabilities that an element of the affine group is separable, cyclic, or semisimple and to study the convergence to these limits. The semisimple limit involves both Rogers-Ramanujan identities. This yields the first examples of such computations for a maximal parabolic subgroup of a finite classical group. (C) 2002 Elsevier Science (USA).