• Bernoulli
  • Volume 22, Number 3 (2016), 1729-1744.

Optimal classification and nonparametric regression for functional data

Alexander Meister

Full-text: Open access


We establish minimax convergence rates for classification of functional data and for nonparametric regression with functional design variables. The optimal rates are of logarithmic type under smoothness constraints on the functional density and the regression mapping, respectively. These asymptotic properties are attainable by conventional kernel procedures. The bandwidth selector does not require knowledge of the smoothness level of the target mapping. In this work, the functional data are considered as realisations of random variables which take their values in a general Polish metric space. We impose certain metric entropy constraints on this space; but no algebraic properties are required.

Article information

Bernoulli, Volume 22, Number 3 (2016), 1729-1744.

Received: April 2014
Revised: December 2014
First available in Project Euclid: 16 March 2016

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

asymptotic optimality kernel methods minimax convergence rates nonparametric estimation topological data


Meister, Alexander. Optimal classification and nonparametric regression for functional data. Bernoulli 22 (2016), no. 3, 1729--1744. doi:10.3150/15-BEJ709.

Export citation


  • [1] Audibert, J.-Y. and Tsybakov, A.B. (2007). Fast learning rates for plug-in classifiers. Ann. Statist. 35 608–633.
  • [2] Benko, M., Härdle, W. and Kneip, A. (2009). Common functional principal components. Ann. Statist. 37 1–34.
  • [3] Berlinet, A., Elamine, A. and Mas, A. (2011). Local linear regression for functional data. Ann. Inst. Statist. Math. 63 1047–1075.
  • [4] Biau, G., Bunea, F. and Wegkamp, M.H. (2005). Functional classification in Hilbert spaces. IEEE Trans. Inform. Theory 51 2163–2172.
  • [5] Biau, G., Cérou, F. and Guyader, A. (2010). Rates of convergence of the functional $k$-nearest neighbor estimate. IEEE Trans. Inform. Theory 56 2034–2040.
  • [6] Bretagnolle, J. and Huber, C. (1979). Estimation des densités: Risque minimax. Z. Wahrsch. Verw. Gebiete 47 119–137.
  • [7] Butucea, C. and Tsybakov, A.B. (2007). Sharp optimality in density deconvolution with dominating bias. I. Teor. Veroyatn. Primen. 52 111–128.
  • [8] Carroll, R.J., Delaigle, A. and Hall, P. (2013). Unexpected properties of bandwidth choice when smoothing discrete data for constructing a functional data classifier. Ann. Statist. 41 2739–2767.
  • [9] Chen, D. and Müller, H.-G. (2012). Nonlinear manifold representations for functional data. Ann. Statist. 40 1–29.
  • [10] Delaigle, A. and Hall, P. (2012). Achieving near perfect classification for functional data. J. R. Stat. Soc. Ser. B. Stat. Methodol. 74 267–286.
  • [11] Delaigle, A. and Hall, P. (2013). Classification using censored functional data. J. Amer. Statist. Assoc. 108 1269–1283.
  • [12] Devroye, L., Györfi, L. and Lugosi, G. (1996). A Probabilistic Theory of Pattern Recognition. Applications of Mathematics (New York) 31. New York: Springer.
  • [13] Fan, J. (1991). On the optimal rates of convergence for nonparametric deconvolution problems. Ann. Statist. 19 1257–1272.
  • [14] Ferraty, F. and Vieu, P. (2006). Nonparametric Functional Data Analysis: Theory and Practice. Springer Series in Statistics. New York: Springer.
  • [15] Ferraty, F., Laksaci, A., Tadj, A. and Vieu, P. (2010). Rate of uniform consistency for nonparametric estimates with functional variables. J. Statist. Plann. Inference 140 335–352.
  • [16] Forzani, L., Fraiman, R. and Llop, P. (2012). Consistent nonparametric regression for functional data under the Stone–Besicovitch conditions. IEEE Trans. Inform. Theory 58 6697–6708.
  • [17] Gao, F. and Wellner, J.A. (2007). Entropy estimate for high-dimensional monotonic functions. J. Multivariate Anal. 98 1751–1764.
  • [18] Hall, P. and Horowitz, J.L. (2007). Methodology and convergence rates for functional linear regression. Ann. Statist. 35 70–91.
  • [19] Kolmogorov, A.N. and Tihomirov, V.M. (1961). $\varepsilon $-entropy and $\varepsilon $-capacity of sets in functional space. Amer. Math. Soc. Transl. (2) 17 277–364.
  • [20] Mas, A. (2012). Lower bound in regression for functional data by representation of small ball probabilities. Electron. J. Stat. 6 1745–1778.
  • [21] Meister, A. (2011). Asymptotic equivalence of functional linear regression and a white noise inverse problem. Ann. Statist. 39 1471–1495.
  • [22] Ramsay, J.O. and Silverman, B.W. (2005). Functional Data Analysis, 2nd ed. Springer Series in Statistics. New York: Springer.
  • [23] Tsybakov, A.B. (2009). Introduction to Nonparametric Estimation. Springer Series in Statistics. New York: Springer.
  • [24] van de Geer, S.A. (2000). Applications of Empirical Process Theory. Cambridge Series in Statistical and Probabilistic Mathematics 6. Cambridge: Cambridge Univ. Press.
  • [25] van der Vaart, A.W. and Wellner, J.A. (1996). Weak Convergence and Empirical Processes with Applications to Statistics. Springer Series in Statistics. New York: Springer.
  • [26] Vapnik, V.N. (1998). Statistical Learning Theory. Adaptive and Learning Systems for Signal Processing, Communications, and Control. New York: Wiley.
  • [27] Yang, Y. (1999). Minimax nonparametric classification. I. Rates of convergence. IEEE Trans. Inform. Theory 45 2271–2284.
  • [28] Yang, Y. (1999). Minimax nonparametric classification. II. Model selection for adaptation. IEEE Trans. Inform. Theory 45 2285–2292.