A simple proof of Pitman–Yor’s Chinese restaurant process from its stick-breaking representation

Caroline Lawless 1  and Julyan Arbel 1
  • 1 Univ. Grenoble Alpes, Inria, CNRS, LJK, 38000, Grenoble, France

Abstract

For a long time, the Dirichlet process has been the gold standard discrete random measure in Bayesian nonparametrics. The Pitman-Yor process provides a simple and mathematically tractable generalization, allowing for a very flexible control of the clustering behaviour. Two commonly used representations of the Pitman-Yor process are the stick-breaking process and the Chinese restaurant process. The former is a constructive representation of the process which turns out very handy for practical implementation, while the latter describes the partition distribution induced. Obtaining one from the other is usually done indirectly with use of measure theory. In contrast, we propose here an elementary proof of Pitman-Yor’s Chinese Restaurant process from its stick-breaking representation.

If the inline PDF is not rendering correctly, you can download the PDF file here.

  • [1] Antoniak, C. E. (1974). Mixtures of Dirichlet processes with applications to Bayesian nonparametric problems. Ann. Statist. 2(6), 1152-1174.

  • [2] Arbel, J., P. De Blasi, and I. Prünster (2018). Stochastic approximations to the Pitman-Yor process. Bayesian Anal., to appear. Available at https://doi.org/10.1214/18-BA1127.

  • [3] Arbel, J., S. Favaro, B. Nipoti, and Y. W. Teh (2017). Bayesian nonparametric inference for discovery probabilities: credible intervals and large sample asymptotics. Statist. Sinica 27(2), 839-858.

  • [4] Bassetti, F., R. Casarin, and F. Leisen (2014). Beta-product dependent Pitman-Yor processes for Bayesian inference. J. Econometrics 180(1), 49-72.

  • [5] Battiston, M., S. Favaro, D. M. Roy, and Y.W. Teh (2018). A characterization of product-form exchangeable feature probability functions. Ann. Appl. Probab. 28(3), 1423-1448.

  • [6] Canale, A., A. Lijoi, B. Nipoti, and I. Prünster (2017). On the Pitman-Yor process with spike and slab base measure. Biometrika 104(3), 681-697.

  • [7] Caron, F., W. Neiswanger, F. Wood, A. Doucet, and M. Davy (2017). Generalized Pólya urn for time-varying Pitman-Yor processes. J. Mach. Learn. Res. 18(27), 1-32.

  • [8] Clauset, A., C. R. Shalizi, and M. E. Newman (2009). Power-law distributions in empirical data. SIAM Rev. 51(4), 661-703.

  • [9] De Blasi, P., S. Favaro, A. Lijoi, R. H. Mena, I. Prünster, and M. Ruggiero (2015). Are Gibbs-type priors the most natural generalization of the Dirichlet process? IEEE Trans. Pattern Anal. Mach. Intell. 37(2), 212-229.

  • [10] De Luca, G. and P. Zuccolotto (2011). A tail dependence-based dissimilarity measure for _nancial time series clustering. Adv. Data Anal. Classif. 5(4), 323-340.

  • [11] Derrida, B. (1981). Random-energy model: An exactly solvable model of disordered systems. Phys. Rev. B 24(5), 2613-2626.

  • [12] Favaro, S., A. Lijoi, R. Mena, and I. Prünster (2009). Bayesian non-parametric inference for species variety with a twoparameter Poisson-Dirichlet process prior. J. R. Stat. Soc. Ser. B. Stat. Methodol. 71(5), 993-1008.

  • [13] Favaro, S. and S. G. Walker (2013). Slice sampling -stable Poisson-Kingman mixture models. J. Comput. Graph. Statist. 22(4), 830-847.

  • [14] Feng, S. and W. Sun (2010). Some diffusion processes associated with two parameter Poisson-Dirichlet distribution and Dirichlet process. Probab. Theory Relat. Fields 148(3-4), 501-525.

  • [15] Ferguson, T. S. (1973). A Bayesian analysis of some nonparametric problems. Ann. Statist. 1(2), 209-230.

  • [16] Ghosal, S. and A. Van der Vaart (2017). Fundamentals of Nonparametric Bayesian Inference. Cambridge University Press.

  • [17] Ishwaran, H. and L. F. James (2001). Gibbs sampling methods for stick-breaking priors. J. Amer. Statist. Assoc. 96(453), 161-173.

  • [18] Jara, A., E. Lesa_re, M. De Iorio, and F. Quintana (2010). Bayesian semiparametric inference for multivariate doubly-intervalcensored data. Ann. Appl. Stat. 4(4), 2126-2149.

  • [19] Kerov, S. V. (2006). Coherent random allocations, and the Ewens-Pitman formula. J. Math. Sci. 138(3), 5699-5710.

  • [20] Kosmidis, I. and D. Karlis (2016). Model-based clustering using copulas with applications. Stat. Comput. 26(5), 1079-1099.

  • [21] Lo, A. Y. (1984). On a class of Bayesian nonparametric estimates: I. Density estimates. Ann. Statist. 12(1), 351-357.

  • [22] Miller, J. W. (2019). An elementary derivation of the Chinese restaurant process from Sethuraman’s stick-breaking process. Statist. Probab. Lett. 146, 112-117.

  • [23] Miller, J.W. and M. T. Harrison (2014). Inconsistency of Pitman-Yor process mixtures for the number of components. J.Mach. Learn. Res. 15(1), 3333-3370.

  • [24] Navarrete, C., F. A. Quintana, and P.Müller (2008). Someissues in nonparametric Bayesian modeling using species sampling models. Stat. Model. 8(1), 3-21.

  • [25] Ni, Y., P. Müller, Y. Zhu, and Y. Ji (2018). Heterogeneous reciprocal graphical models. Biometrics 74(2), 606-615.

  • [26] Perman, M., J. Pitman, and M. Yor (1992). Size-biased sampling of Poisson point processes and excursions. Probab. Theory Relat. Fields 92(1), 21-39.

  • [27] Petrov, L. A. (2009). Two-parameter family of infinite-dimensional diffusions on the Kingman simplex. Funct. Anal. Appl. 43(4), 279-296.

  • [28] Pitman, J. (1995). Exchangeable and partially exchangeable random partitions. Probab. Theory Relat. Fields 102(2), 145-158.

  • [29] Pitman, J. (2003). Poisson-Kingman partitions. In Statistics and Science: a Festschrift for Terry Speed, pp.1-34. IMS, Beachwood OH.

  • [30] Pitman, J. and M. Yor (1997). The two-parameter Poisson-Dirichlet distribution derived from a stable subordinator. Ann. Probab. 25(2), 855-900. [31] Scarpa, B. and D. B. Dunson (2009). Bayesian hierarchical functional data analysis via contaminated informative priors. Biometrics 65(3), 772-780.

  • [32] Scricciolo, C. (2014). Adaptive Bayesian density estimation in Lp-metrics with Pitman-Yor or normalized inverse-Gaussian process kernel mixtures. Bayesian Anal. 9(2), 475-520.

  • [33] Sethuraman, J. (1994). A constructive de_nition of Dirichlet priors. Statist. Sinica 4(2), 639-650.

  • [34] Sudderth, E. B. and M. I. Jordan (2009). Shared segmentation of natural scenes using dependent Pitman-Yor processes. In D. Koller, D. Schuurmans, Y. Bengio and L. Bottou (Eds.), Advances in Neural Information Processing Systems 21, pp. 1585-1592. Curran Associates, Red Hook NY.

  • [35] Teh, Y. W. (2006). A hierarchical Bayesian language model based on Pitman-Yor processes. In Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics, pp. 985-992. Association for Computational Linguistics, Stroudsburg PA.

  • [36] Vershik, A., M. Yor, and N. Tsilevich (2004). On the Markov-Krein identity and quasi-invariance of the gamma process. J. Math. Sci. 121(3), 2303-2310.

  • [37] Wood, F., J. Gasthaus, C. Archambeau, L. James, and Y. W. Teh (2011). The sequence memoizer. Comm. ACM 54(2), 91-98.

OPEN ACCESS

Journal + Issues

Search