Advertisement

Probability Theory and Related Fields

, Volume 174, Issue 3–4, pp 1033–1090 | Cite as

Optimal graphon estimation in cut distance

  • Olga KloppEmail author
  • Nicolas Verzelen
Article
  • 120 Downloads

Abstract

Consider the twin problems of estimating the connection probability matrix of an inhomogeneous random graph and the graphon of a W-random graph. We establish the minimax estimation rates with respect to the cut metric for classes of block constant matrices and step function graphons. Surprisingly, our results imply that, from the minimax point of view, the raw data, that is, the adjacency matrix of the observed graph, is already optimal and more involved procedures cannot improve the convergence rates for this metric. This phenomenon contrasts with optimal rates of convergence with respect to other classical distances for graphons such as the \(l_1\) or \(l_2\) metrics.

Keywords

Inhomogeneous random graph Graphon W-random graphs Networks Stochastic block model Cut distance 

Mathematics Subject Classification

Primary 62G05 Secondary 60C05 

Supplementary material

References

  1. 1.
    Airoldi, E.M., Costa, T.B., Chan, S.H.: Stochastic blockmodel approximation of a graphon: theory and consistent estimation. In: Advances in Neural Information Processing Systems, pp. 692–700 (2013)Google Scholar
  2. 2.
    Alon, N., De La Vega, W.F., Kannan, R., Karpinski, M.: Random sampling and approximation of MAX-CSPS. J. Comput. Syst. Sci. 67(2), 212–243 (2003)MathSciNetzbMATHCrossRefGoogle Scholar
  3. 3.
    Bandeira, A.S., van Handel, R.: Sharp nonasymptotic bounds on the norm of random matrices with independent entries. Ann. Probab. 44(4), 2479–2506 (2016)MathSciNetzbMATHCrossRefGoogle Scholar
  4. 4.
    Bickel, P.J., Chen, A.: A nonparametric view of network models and Newman–Girvan and other modularities. Proc. Natl. Acad. Sci. 106(50), 21068–21073 (2009)zbMATHCrossRefGoogle Scholar
  5. 5.
    Bickel, P.J., Chen, A., Levina, E.: The method of moments and degree distributions for network models. Ann. Stat. 39(5), 2280–2301 (2011)MathSciNetzbMATHCrossRefGoogle Scholar
  6. 6.
    Bollobás, B., Janson, S., Riordan, O.: The phase transition in inhomogeneous random graphs. Random Struct. Algorithms 31(1), 3–122 (2007)MathSciNetzbMATHCrossRefGoogle Scholar
  7. 7.
    Borgs, C., Chayes, J.T., Cohn, H., Ganguly, S.: Consistent nonparametric estimation for heavy-tailed sparse graphs. ArXiv e-prints (2015)Google Scholar
  8. 8.
    Borgs, C., Chayes, J.T., Lovász, L., Sós, V.T., Vesztergombi, K.: Convergent sequences of dense graphs. I. Subgraph frequencies, metric properties and testing. Adv. Math. 219(6), 1801–1851 (2008)MathSciNetzbMATHCrossRefGoogle Scholar
  9. 9.
    Borgs, C., Chayes, J.T., Lovász, L., Sós, V.T., Vesztergombi, K.: Convergent sequences of dense graphs II. Multiway cuts and statistical physics. Ann. Math. (2) 176(1), 151–219 (2012)MathSciNetzbMATHCrossRefGoogle Scholar
  10. 10.
    Borgs, C., Chayes, J., Smith, A.: Private graphon estimation for sparse graphs. In: Advances in Neural Information Processing Systems, pp. 1369–1377 (2015)Google Scholar
  11. 11.
    Borgs, C., Chayes, J.T., Cohn, H., Zhao, Y.: An LP theory of sparse graph convergence I: limits, sparse random graph models, and power law distributions. (2014). arXiv preprint arXiv:1401.2906
  12. 12.
    Borgs, C., Chayes, J.T., Cohn, H., Zhao, Y.: An LP theory of sparse graph convergence. II: LD convergence, quotients, and right convergence. (2014). arXiv preprint arXiv:1408.0744
  13. 13.
    Boucheron, S., Lugosi, G., Massart, P.: Concentration inequalities using the entropy method. Ann. Probab. 31(3), 1583–1614 (2003)MathSciNetzbMATHCrossRefGoogle Scholar
  14. 14.
    Cai, D., Ackerman, N., Freer, C.: An iterative step-function estimator for graphons. (2014). arXiv preprint arXiv:1412.2129
  15. 15.
    Chan, S.H., Airoldi, E.M.: A consistent histogram estimator for exchangeable graph models. In: Proceedings of the 31st International Conference on Machine Learning, pp. 208–216 (2014)Google Scholar
  16. 16.
    Chatterjee, S.: Matrix estimation by universal singular value thresholding. Ann. Stat. 43(1), 177–214 (2015)MathSciNetzbMATHCrossRefGoogle Scholar
  17. 17.
    Choi, D.S., Wolfe, P.J., Airoldi, E.M.: Stochastic blockmodels with a growing number of classes. Biometrika 99(2), 273–284 (2012)MathSciNetzbMATHCrossRefGoogle Scholar
  18. 18.
    Diaconis, P., Janson, S.: Graph limits and exchangeable random graphs. (2007). arXiv preprint arXiv:0712.2749
  19. 19.
    Frieze, A., Kannan, R.: Quick approximation to matrices and applications. Combinatorica 19(2), 175–220 (1999)MathSciNetzbMATHCrossRefGoogle Scholar
  20. 20.
    Gao, C., Lu, Y., Zhou, H.H.: Rate-optimal graphon estimation. Ann. Stat. 43(6), 2624–2652 (2015)MathSciNetzbMATHCrossRefGoogle Scholar
  21. 21.
    Guédon, O., Vershynin, R.: Community detection in sparse networks via Grothendieck’s inequality. Probab. Theory Relat. Fields 165(3), 1025–1049 (2016)MathSciNetzbMATHCrossRefGoogle Scholar
  22. 22.
    Hoff, P.D., Raftery, A.E., Handcock, M.S.: Latent space approaches to social network analysis. J. Am. Stat. Assoc. 97(460), 1090–1098 (2002)MathSciNetzbMATHCrossRefGoogle Scholar
  23. 23.
    Holland, P.W., Laskey, K.B., Leinhardt, S.: Stochastic blockmodels: first steps. Soc. Netw. 5(2), 109–137 (1983)MathSciNetCrossRefGoogle Scholar
  24. 24.
    Janson, S.: Graphons, Cut Norm and Distance, Couplings and Rearrangements, Volume 4 of New York. Journal of Mathematics. NYJM Monographs. State University of New York, University at Albany, Albany (2013)Google Scholar
  25. 25.
    Klopp, O.: Rank penalized estimators for high-dimensional matrices. Electron. J. Stat. 5, 1161–1183 (2011)MathSciNetzbMATHCrossRefGoogle Scholar
  26. 26.
    Klopp, O., Tsybakov, A.B., Verzelen, N.: Oracle inequalities for network models and sparse graphon estimation. Ann. Stat. 45(1), 316–354 (2017)MathSciNetzbMATHCrossRefGoogle Scholar
  27. 27.
    Latouche, P., Robin, S.: Bayesian Model Averaging of Stochastic Block Models to Estimate the Graphon Function and Motif Frequencies in a W-Graph Model. Technical report (2013)Google Scholar
  28. 28.
    Lovász, L.: Large Networks and Graph Limits, Volume 60 of American Mathematical Society Colloquium Publications. American Mathematical Society, Providence (2012)Google Scholar
  29. 29.
    Lovász, L., Szegedy, B.: Limits of dense graph sequences. J. Combin. Theory Ser. B 96(6), 933–957 (2006)MathSciNetzbMATHCrossRefGoogle Scholar
  30. 30.
    Szarek, S.J.: On the best constants in the Khinchin inequality. Stud. Math. 58(2), 197–208 (1976)MathSciNetzbMATHCrossRefGoogle Scholar
  31. 31.
    Szemerédi, E.: Regular Partitions of Graphs. Technical report, DTIC Document (1975)Google Scholar
  32. 32.
    Tsybakov, A.B.: Introduction to Nonparametric Estimation. Springer Series in Statistics. Springer, New York (2009). Revised and extended from the 2004 French original, Translated by Vladimir ZaiatsGoogle Scholar
  33. 33.
    Wolfe, P.J., Olhede, S.C.: Nonparametric Graphon Estimation. (2013). arXiv preprint arXiv:1309.5936
  34. 34.
    Yang, J., Han, C., Airoldi, E.M.: Nonparametric estimation and testing of exchangeable graph models. In: AISTATS (2014)Google Scholar
  35. 35.
    Zhang, Y., Levina, E., Zhu, J.: Estimating Network Edge Probabilities by Neighborhood Smoothing. (2015). arXiv preprint arXiv:1509.08588

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.ESSEC Business SchoolCergyFrance
  2. 2.CRESTPalaiseauFrance
  3. 3.INRA, UMR 729 MISTEAMontpellierFrance

Personalised recommendations