Concentration in the Generalized Chinese Restaurant Process

Abstract: The Generalized Chinese Restaurant Process (GCRP) describes a sequence of exchangeable random partitions of the numbers ${1,\dots,n}$. This process is related to the Ewens sampling model in Genetics and to Bayesian nonparametric methods such as topic models. In this paper, we study the GCRP in a regime where the number of parts grows like $n^\alpha$ with $\alpha>0$. We prove a non-asymptotic concentration result for the number of parts of size $k=o(n^{\alpha/(2\alpha+4)}/(\log n)^{1/(2+\alpha)})$. In particular, we show that these random variables concentrate around $c_{k}\,V_\,n^\alpha$ where $V_\,n^\alpha$ is the asymptotic number of parts and $c_k\approx k^{-(1+\alpha)}$ is a positive value depending on $k$. We also obtain finite-$n$ bounds for the total number of parts. Our theorems complement asymptotic statements by Pitman and more recent results on large and moderate deviations by Favaro, Feng and Gao.