Electronic Journal of Statistics

Adaptive estimation of convex polytopes and convex sets from noisy data

Victor-Emmanuel Brunel

Full-text: Open access


We estimate convex polytopes and general convex sets in $\mathbb{R}^{d}$, $d\geq 2$ in the regression framework. We measure the risk of our estimators using a $L^{1}$-type loss function and prove upper bounds on these risks. We show, in the case of convex polytopes, that these estimators achieve the minimax rate. For convex polytopes, this minimax rate is $\frac{\ln n}{n}$, which differs from the parametric rate for non-regular families by a logarithmic factor, and we show that this extra factor is essential. Using polytopal approximations we extend our results to general convex sets, and we achieve the minimax rate up to a logarithmic factor. In addition we provide an estimator that is adaptive with respect to the number of vertices of the unknown polytope, and we prove that this estimator is optimal in all classes of convex polytopes with a given number of vertices.

Article information

Electron. J. Statist., Volume 7 (2013), 1301-1327.

First available in Project Euclid: 10 May 2013

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

Adaptive estimation approximation convex set minimax polytope regression


Brunel, Victor-Emmanuel. Adaptive estimation of convex polytopes and convex sets from noisy data. Electron. J. Statist. 7 (2013), 1301--1327. doi:10.1214/13-EJS804. https://projecteuclid.org/euclid.ejs/1368193533

Export citation


  • [1] Alon N., Spencer J. H. (2008) The probabilistic method, Wiley.
  • [2] Bárány I. (2007) Random Polytopes, convex bodies, and approximation, in Baddeley, A. J., Bárány, I., Shneider, R., Weil, W. (2004) Stochastic Geometry, C.I.M.E. Summer School, Martina Franca, Italy (W. Weil, ed.), Lecture Notes in Mathematics 1892, pp. 77-118, Springer, Berlin.
  • [3] Berger M. (1978) Géométrie, Tome 3: Convexes et polytopes, polyèdres réguliers, aires et volumes, Ed. Cedic/Fernand, Nathan.
  • [4] Bronshtein E. M. (1976) $\epsilon$-entropy of convex sets and functions, Siberian Mathematical Journal 17, 393-398.
  • [5] Chichignoud M. (2010) Performances statistiques d’estimateurs non-linéaires, Thèse de Doctorat, Université de Provence U.F.R. M.I.M., available at, http://stat.ethz.ch/people/michaech/PDF_thesis.
  • [6] Cuevas A. (2009) Set estimation: Another bridge between statistics and geometry, Boletín de Estadística e Investigación Operativa, Vol. 25, No. 2, pp., 71-85.
  • [7] Cuevas A., Fraiman R. (2010) Set estimation, in New Perspectives on Stochastic Geometry, W.S. Kendall and I. Molchanov, eds., pp. 374-397 Oxford University, Press.
  • [8] Cuevas A., Rodríguez-Casal A. (2004). On boundary estimation. Adv. in Appl. Probab. 36, pp., 340-354.
  • [9] Dudley R. M. (1974) Metric Entropy of Some Classes of Sets with Differentiable Boundaries, Journal of Approximation Theory 10, 227-236.
  • [10] Efron B. (1965) The Convex Hull of a Random Set of Points, Biometrika, Vol. 52, No 3/4, pp., 331-343.
  • [11] Gordon Y., Meyer M., Reisner, S. (1995) Constructing a Polytope to Approximate a Convex Body, Geometricae Dedicata 57: 217-222, 1995.
  • [12] Guntuboyina A. (2011) Lower bounds for the minimax risk using f-divergences, and applications. IEEE Transactions on Information Theory, vol. 57, pages, 2386-2399
  • [13] Ibragimov I. A., Khasminiskii R. Z. (1984) Statistical Estimation: Asymptotic Theory, New York:, Springer-Verlag.
  • [14] Janson S. (1987) Maximal spacings in several dimensions, The Annals of Probability, Vol. 15, No. 1, pp., 274-280.
  • [15] Kendall W. S., Molchanov I. (2010) New Perspectives in Stochastic Geometry. Eds., Oxford University, Press.
  • [16] Kendall M. G., Moran P. A. P. (1963) Geometrical Probability, Griffin’s Statistical Monographs and Courses, no.10.
  • [17] Kolmogorov A. N., Tikhomirov V. M. (1959) $\varepsilon$-entropy and $\varepsilon$-capacity of sets in function spaces, Uspekhi Mat. Nauk, 14:2(86), 3–86 (in, Russian).
  • [18] Korostelev A. P., Tsybakov A. B. (1992) Asymptotically minimax image reconstruction problems. In Topics in Nonparametric Estimation (R. Z. Khasminskii, ed.) 45-86. Amer. Math. Soc., Providence, RI.
  • [19] Korostelev A. P., Tsybakov A. B. (1993) Minimax Theory of Image Reconstruction. Lecture Notes in Statistics, v.82. Springer, NY, e.a.
  • [20] Korostelev A. P., Tsybakov A. B. (1994) Asymptotic efficiency in estimation of a convex set (in russian), Problems of Information Transmission, v.30, n.4, 317-327.
  • [21] Lepski O. V. (1991) Asymptotically minimax adaptive estimation i. upper bounds. optimally adaptive estimates. Theory Probab. Appl., 36:682-697.
  • [22] Mammen E., Tsybakov A. (1995) Asymptotical Minimax Recovery of Sets with Smooth Boundaries, The Annals of Statistics, Vol. 23, No. 2, pp., 502-524.
  • [23] McClure D. E., Vitale R. A. (1975) Polygonal Approximation of Plane Convex Bodies, Journal of Mathematical Analysis and Applications, Vol. 51, No.2.
  • [24] Pateiro-López B. (2008) Set estimation under convexity type restrictions, PhD thesis, available at, http://eio.usc.es/pub/pateiro/files/THESIS_BeatrizPateiroLopez.pdf.
  • [25] Reisner S., Schütt C., Werner E. (2001) Dropping a vertex or a facet from a convex polytope, Forum Math., 359-378.
  • [26] Rényi A., Sulanke R. (1963) Über die konvexe Hülle von $n$ zufällig gewählten Punkten. Z.Wahrscheinlichkeitsth. Verw. Geb. 2 pp., 75-84.
  • [27] Rényi A., Sulanke R. (1964) Über die konvexe Hülle von $n$ zufällig gewählten Punkten. II, Z.Wahrscheinlichkeitsth. Verw. Geb. 3 pp., 138-147.
  • [28] Tsybakov A. B. (2009) Introduction to nonparametric estimation, Springer.