Bernoulli

  • Bernoulli
  • Volume 24, Number 1 (2018), 386-407.

The maximum likelihood threshold of a graph

Elizabeth Gross and Seth Sullivant

Full-text: Access denied (no subscription detected)

We're sorry, but we are unable to provide you with the full text of this article because we are not able to identify you as a subscriber. If you have a personal subscription to this journal, then please login. If you are already logged in, then you may need to update your profile to register your subscription. Read more about accessing full-text

Abstract

The maximum likelihood threshold of a graph is the smallest number of data points that guarantees that maximum likelihood estimates exist almost surely in the Gaussian graphical model associated to the graph. We show that this graph parameter is connected to the theory of combinatorial rigidity. In particular, if the edge set of a graph $G$ is an independent set in the $(n-1)$-dimensional generic rigidity matroid, then the maximum likelihood threshold of $G$ is less than or equal to $n$. This connection allows us to prove many results about the maximum likelihood threshold. We conclude by showing that these methods give exact bounds on the number of observations needed for the score matching estimator to exist with probability one.

Article information

Source
Bernoulli, Volume 24, Number 1 (2018), 386-407.

Dates
Received: September 2015
Revised: June 2016
First available in Project Euclid: 27 July 2017

Permanent link to this document
https://projecteuclid.org/euclid.bj/1501142448

Digital Object Identifier
doi:10.3150/16-BEJ881

Mathematical Reviews number (MathSciNet)
MR3706762

Zentralblatt MATH identifier
06778333

Keywords
algebraic matroids Gaussian graphical models matrix completion maximum likelihood estimation maximum likelihood threshold rigidity theory score matching estimator weak maximum likelihood threshold

Citation

Gross, Elizabeth; Sullivant, Seth. The maximum likelihood threshold of a graph. Bernoulli 24 (2018), no. 1, 386--407. doi:10.3150/16-BEJ881. https://projecteuclid.org/euclid.bj/1501142448


Export citation

References

  • [1] Alon, N., McDiarmid, C. and Reed, B. (1991). Acyclic coloring of graphs. Random Structures Algorithms 2 277–288.
  • [2] Ben-David, E. (2015). Sharp lower and upper bounds for the Gaussian rank of a graph. J. Multivariate Anal. 139 207–218.
  • [3] Buhl, S.L. (1993). On the existence of maximum likelihood estimators for graphical Gaussian models. Scand. J. Stat. 20 263–270.
  • [4] Connelly, R. and Whiteley, W.J. (2010). Global rigidity: The effect of coning. Discrete Comput. Geom. 43 717–735.
  • [5] Dehn, M. (1916). Über die Starrheit konvexer Polyeder. Math. Ann. 77 466–473.
  • [6] Dempster, A.P. (1972). Covariance selection. Biometrics 28 157–175.
  • [7] Dobra, A., Hans, C., Jones, B., Nevins, J.R., Yao, G. and West, M. (2004). Sparse graphical models for exploring gene expression data. J. Multivariate Anal. 90 196–212.
  • [8] Forbes, P.G.M. and Lauritzen, S. (2015). Linear estimating equations for exponential families with application to Gaussian linear concentration models. Linear Algebra Appl. 473 261–283.
  • [9] Friedman, J., Hastie, T. and Tibsharani, T. (2008). Sparse inverse covariance estimation with the graphical lasso. Biostatistics 9 432–441.
  • [10] Gluck, H. (1975). Almost all simply connected closed surfaces are rigid. In Geometric Topology (Proc. Conf., Park City, Utah, 1974). Lecture Notes in Math. 438 225–239. Berlin: Springer.
  • [11] Graver, J., Servatius, B. and Servatius, H. (1993). Combinatorial Rigidity. Graduate Studies in Mathematics 2. Providence, RI: Amer. Math. Soc.
  • [12] Grünbaum, B. (1973). Acyclic colorings of planar graphs. Israel J. Math. 14 390–408.
  • [13] Hyvärinen, A. (2005). Estimation of non-normalized statistical models by score matching. J. Mach. Learn. Res. 6 695–709.
  • [14] Jackson, B., Jordán, T. and Tanigawa, S. (2014). Combinatorial conditions for the unique completability of low-rank matrices. SIAM J. Discrete Math. 28 1797–1819.
  • [15] Jacobs, D.J. and Hendrickson, B. (1997). An algorithm for two-dimensional rigidity percolation: The pebble game. J. Comput. Phys. 137 346–365.
  • [16] Kalai, G., Nevo, E. and Novik, I. (2016). Bipartite rigidity. Trans. Amer. Math. Soc. 368 5515–5545.
  • [17] Király, F., Rosen, Z. and Theran, L. (2013). Algebraic matroids with graph symmetry. Preprint. Available at arXiv:1312.3777.
  • [18] Király, F.J., Theran, L. and Tomioka, R. (2015). The algebraic combinatorial approach for low-rank matrix completion. J. Mach. Learn. Res. 16 1391–1436.
  • [19] Krumsiek, J., Suhre, K., Illig, T., Adamski, J. and Theis, F.J. (2011). Gaussian graphical modeling reconstructs pathway reactions from high-throughput metabolomics data. BMC Syst. Biol. 5.
  • [20] Laman, G. (1970). On graphs and rigidity of plane skeletal structures. J. Engrg. Math. 4 331–340.
  • [21] Lauritzen, S.L. (1996). Graphical Models. Oxford Statistical Science Series 17. New York: Oxford Univ. Press.
  • [22] Oxley, J. (2011). Matroid Theory, 2nd ed. Oxford Graduate Texts in Mathematics 21. Oxford: Oxford Univ. Press.
  • [23] Schäfer, J. and Strimmer, K. (2005). An empirical Bayes approach to inferring large-scale gene association networks. Bioinformatics 21 754–764.
  • [24] Singer, A. and Cucuringu, M. (2009/2010). Uniqueness of low-rank matrix completion by rigidity theory. SIAM J. Matrix Anal. Appl. 31 1621–1641.
  • [25] Uhler, C. (2012). Geometry of maximum likelihood estimation in Gaussian graphical models. Ann. Statist. 40 238–261.
  • [26] Welsh, D.J.A. (1976). Matroid Theory. London: Academic Press.
  • [27] Whiteley, W. (1983). Cones, infinity and $1$-story buildings. Topol. Struct. 8 53–70.
  • [28] Whiteley, W. (1996). Some matroids from discrete applied geometry. In Matroid Theory (Seattle, WA, 1995). Contemp. Math. 197 171–311. Providence, RI: Amer. Math. Soc.
  • [29] Whittaker, J. (1990). Graphical Models in Applied Multivariate Statistics. Chichester: Wiley.
  • [30] Wu, X., Ye, Y. and Subramanian, K.R. (2003). Interactive analysis of gene interactions using graphical Gaussian model. Proceedings of the ACM SIGKDD Workshop on Data Mining in Bioinformatics 3 63–69.
  • [31] Ziegler, G.M. (1995). Lectures on Polytopes. Graduate Texts in Mathematics 152. New York: Springer.