Trabs, Mathias
Information bounds for inverse problems with application to deconvolution and Lévy models
Annales de l'I.H.P. Probabilités et statistiques, Tome 51 (2015) no. 4 , p. 1620-1650
Le texte intégral des articles récents est réservé aux abonnés de la revue. Consulter l'article sur le site de la revue
MR 3414460
doi : 10.1214/14-AIHP627
URL stable : http://www.numdam.org/item?id=AIHPB_2015__51_4_1620_0

Si une fonctionnelle dans un problème inverse non-paramétrique peut être estimée à vitesse paramétrique, alors la vitesse minimax ne donne aucune information sur le caractère mal posé du problème. Pour avoir une borne inférieure plus précise, nous étudions l’efficacité semi-paramétrique dans le sens de Hájek–Le Cam pour l’estimation fonctionnelle dans des modèles indirects réguliers. Ces derniers sont caractérisés comme modèles que l’on peut approcher localement par un modèle linéaire de bruit blanc décrit par l’opérateur de score généralisé. Un théorème de convolution pour des modèles indirects réguliers est prouvé. Ceci s’applique à une large classe de problèmes statistiques inverses, comme montré pour les modèles prototypes du bruit blanc et de la déconvolution. Il est spécialement utile pour des modèles non-linéaires. Nous discutons en détails un modèle non-linéaire de déconvolution où un processus de Lévy est observé à basse fréquence, en obtenant une borne d’information pour l’estimation de fonctionnelles linéaires de la mesure de sauts.
If a functional in a nonparametric inverse problem can be estimated with parametric rate, then the minimax rate gives no information about the ill-posedness of the problem. To have a more precise lower bound, we study semiparametric efficiency in the sense of Hájek–Le Cam for functional estimation in regular indirect models. These are characterized as models that can be locally approximated by a linear white noise model that is described by the generalized score operator. A convolution theorem for regular indirect models is proved. This applies to a large class of statistical inverse problems, which is illustrated for the prototypical white noise and deconvolution model. It is especially useful for nonlinear models. We discuss in detail a nonlinear model of deconvolution type where a Lévy process is observed at low frequency, concluding an information bound for the estimation of linear functionals of the jump measure.

Bibliographie

[1] D. Belomestny and M. Reiß. Spectral calibration of exponential Lévy models. Finance Stoch. 10 (4) (2006) 449–474. MR 2276314 | Zbl 1126.91022

[2] P. J. Bickel, C. A. J. Klaassen, Y. Ritov and J. A. Wellner. Efficient and Adaptive Estimation for Semiparametric Models. Springer, New York, 1998. MR 1623559 | Zbl 0894.62005

[3] N. Bissantz, T. Hohage and A. Munk. Consistency and rates of convergence of nonlinear Tikhonov regularization with random noise. Inverse Probl. 20 (6) (2004) 1773–1789. MR 2107236 | Zbl 1077.65060

[4] L. D. Brown and M. G. Low. Asymptotic equivalence of nonparametric regression and white noise. Ann. Statist. 24 (6) (1996) 2384–2398. MR 1425958 | Zbl 0867.62022

[5] B. Buchmann and R. Grübel. Decompounding: An estimation problem for Poisson random sums. Ann. Statist. 31 (4) (2003) 1054–1074. MR 2001642 | Zbl 1105.62309

[6] L. Cavalier. Nonparametric statistical inverse problems. Inverse Probl. 24 (3) 034004 (2008). MR 2421941 | Zbl 1137.62323

[7] L. Cavalier, G. K. Golubev, D. Picard and A. B. Tsybakov. Oracle inequalities for inverse problems. Ann. Statist. 30 (3) (2002) 843–874. MR 1922543 | Zbl 1029.62032

[8] E. Clément, S. Delattre and A. Gloter. An infinite dimensional convolution theorem with applications to the efficient estimation of the integrated volatility. Stochastic Process. Appl. 123 (7) (2013) 2500–2521. MR 3054534 | Zbl 1284.62290

[9] G. Da Prato and J. Zabczyk. Stochastic Equations in Infinite Dimensions. Encyclopedia of Mathematics and Its Applications 44. Cambridge Univ. Press, Cambridge, 1992. MR 1207136 | Zbl 0761.60052

[10] H. W. Engl, M. Hanke and A. Neubauer. Regularization of Inverse Problems. Mathematics and Its Applications 375. Kluwer Academic, Dordrecht, 1996. MR 1408680 | Zbl 0859.65054

[11] J. Fan. On the optimal rates of convergence for nonparametric deconvolution problems. Ann. Statist. 19 (3) (1991) 1257–1272. MR 1126324 | Zbl 0729.62033

[12] E. Giné and R. Nickl. Uniform central limit theorems for kernel density estimators. Probab. Theory Related Fields 141 (3–4) (2008) 333–387. MR 2391158 | Zbl 1141.62022

[13] A. Goldenshluger and S. V. Pereverzev. Adaptive estimation of linear functionals in Hilbert scales from indirect white noise observations. Probab. Theory Related Fields 118 (2) (2000) 169–186. MR 1790080 | Zbl 1055.62523

[14] A. Goldenshluger and S. V. Pereverzev. On adaptive inverse estimation of linear functionals in Hilbert scales. Bernoulli 9 (5) (2003) 783–807. MR 2047686 | Zbl 1055.62034

[15] J. Jacod. Une application de la topologie d’Emery: le processus information d’un modèle statistique filtré. In Séminaire de Probabilités, XXIII 448–474. Lecture Notes in Math. 1372. Springer, Berlin, 1989. Numdam | MR 1022931 | Zbl 0739.62073

[16] J. Jacod. Regularity, partial regularity, partial information process, for a filtered statistical model. Probab. Theory Related Fields 86 (3) (1990) 305–335. MR 1069284 | Zbl 0677.62001

[17] J. Jacod and A. N. Shiryaev. Limit Theorems for Stochastic Processes, 2nd edition. Grundlehren der Mathematischen Wissenschaften [Fundamental Principles of Mathematical Sciences] 288. Springer, Berlin, 2003. MR 1943877 | Zbl 1018.60002

[18] A. Khoujmane, F. Ruymgaart and M. Shubov. The convolution theorem for estimating linear functionals in indirect nonparametric regression models. J. Statist. Plann. Inference 137 (3) (2007) 811–820. MR 2301717 | Zbl 1104.62041

[19] C. A. J. Klaassen, E.-J. Lee and F. H. Ruymgaart. On efficiency of indirect estimation of nonparametric regression functions. In Algebraic Methods in Statistics and Probability (Notre Dame, IN, 2000) 173–184. Contemp. Math. 287. Amer. Math. Soc., Providence, RI, 2001. MR 1873675 | Zbl 1023.62047

[20] C. A. J. Klaassen, E.-J. Lee and F. H. Ruymgaart. Asymptotically efficient estimation of linear functionals in inverse regression models. J. Nonparametr. Stat. 17 (7) (2005) 819–831. MR 2180367 | Zbl 1116.62040

[21] H. H. Kuo. Gaussian Measures in Banach Spaces. Lecture Notes in Math. 463. Springer, Berlin, 1975. MR 461643 | Zbl 0306.28010

[22] L. Le Cam. Limits of experiments. In Proceedings of the Sixth Berkeley Symposium on Mathematical Statistics and Probability (Univ. California, Berkeley, Calif., 1970/1971), Vol. I: Theory of Statistics 245–261. Univ. California Press, Berkeley, CA, 1972. Zbl 0271.62004

[23] F. Liese. Estimates of Hellinger integrals of infinitely divisible distributions. Kybernetika (Prague) 23 (3) (1987) 227–238. MR 900332 | Zbl 0638.60002

[24] A. Meister. Deconvolution Problems in Nonparametric Statistics. Lecture Notes in Statist. Springer, Berlin, 2009. MR 2768576 | Zbl 1178.62028

[25] F. Natterer. Error bounds for Tikhonov regularization in Hilbert scales. Appl. Anal. 18 (1–2) (1984) 29–37. MR 762862 | Zbl 0504.65031

[26] M. H. Neumann and M. Reiß. Nonparametric estimation for Lévy processes from low-frequency observations. Bernoulli 15 (1) (2009) 223–248. MR 2546805 | Zbl 1200.62095

[27] R. Nickl and M. Reiß. A Donsker theorem for Lévy measures. J. Funct. Anal. 263 (10) (2012) 3306–3332. MR 2973342 | Zbl 06110218

[28] M. Nussbaum. Asymptotic equivalence of density estimation and Gaussian white noise. Ann. Statist. 24 (6) (1996) 2399–2430. MR 1425959 | Zbl 0867.62035

[29] M. Reiß. Testing the characteristics of a Lévy process. Stochastic Process. Appl. 123 (7) (2013) 2808–2828. MR 3054546 | Zbl 1294.62179

[30] K.-I. Sato. Lévy Processes and Infinitely Divisible Distributions. Cambridge Univ. Press, Cambridge, 1999. MR 1739520 | Zbl 1287.60003

[31] J. Söhl and M. Trabs. A uniform central limit theorem and efficiency for deconvolution estimators. Electron. J. Stat. 6 (2012) 2486–2518. MR 3020273 | Zbl 1295.62034

[32] M. Trabs. Calibration of self-decomposable Lévy models. Bernoulli 20 (1) (2014) 109–140. MR 3160575 | Zbl 1285.62101

[33] A. W. Van Der Vaart. Statistical Estimation in Large Parameter Spaces. CWI Tract 44. Stichting Mathematisch Centrum, Centrum voor Wiskunde en Informatica, Amsterdam, 1988. MR 927725 | Zbl 0629.62035

[34] A. W. Van Der Vaart. On differentiable functionals. Ann. Statist. 19 (1) (1991) 178–204. MR 1091845 | Zbl 0732.62035

[35] A. W. Van Der Vaart. Asymptotic Statistics. Cambridge Series in Statistical and Probabilistic Mathematics. Cambridge Univ. Press, Cambridge, 1998. MR 1652247 | Zbl 0910.62001

[36] A. W. Van Der Vaart and J. A. Wellner. Weak Convergence and Empirical Processes. Springer Series in Statistics. Springer, New York, 1996. MR 1385671 | Zbl 0862.60002

[37] A. C. M. Van Rooij, F. H. Ruymgaart and W. R. Van Zwet. Asymptotic efficiency of inverse estimators. Teor. Veroyatn. Primen. 44 (4) (1999) 826–844. Translation in Theory Probab. Appl. 44 (4) 722–738. MR 1811134 | Zbl 1045.62041

[38] H. Witting. Mathematische Statistik. I: Parametrische Verfahren bei festem Stichprobenumfang. B. G. Teubner, Stuttgart, 1985. MR 943833 | Zbl 0581.62001