This paper deals with the density estimation on $\mathbb{R}^{d}$ under sup-norm loss. We provide a fully data-driven estimation procedure and establish for it a so-called sup-norm oracle inequality. The proposed estimator allows us to take into account not only approximation properties of the underlying density, but eventual independence structure as well. Our results contain, as a particular case, the complete solution of the bandwidth selection problem in the multivariate density model. Usefulness of the developed approach is illustrated by application to adaptive estimation over anisotropic Nikolskii classes.
References
Akakpo, N. (2012). Adaptation to anisotropy and inhomogeneity via dyadic piecewise polynomial selection. Math. Methods Statist. 21 1–28. MR2901269 10.3103/S1066530712010012Akakpo, N. (2012). Adaptation to anisotropy and inhomogeneity via dyadic piecewise polynomial selection. Math. Methods Statist. 21 1–28. MR2901269 10.3103/S1066530712010012
Birgé, L. (2008). Model selection for density estimation with $\mathbb{L}_{2}$-loss. Available at arXiv:0808.1416v2. 0808.1416v2Birgé, L. (2008). Model selection for density estimation with $\mathbb{L}_{2}$-loss. Available at arXiv:0808.1416v2. 0808.1416v2
Devroye, L. and Lugosi, G. (1996). A universally acceptable smoothing factor for kernel density estimates. Ann. Statist. 24 2499–2512. MR1425963 0867.62024 10.1214/aos/1032181164 euclid.aos/1032181164
Devroye, L. and Lugosi, G. (1996). A universally acceptable smoothing factor for kernel density estimates. Ann. Statist. 24 2499–2512. MR1425963 0867.62024 10.1214/aos/1032181164 euclid.aos/1032181164
Devroye, L. and Lugosi, G. (1997). Nonasymptotic universal smoothing factors, kernel complexity and Yatracos classes. Ann. Statist. 25 2626–2637. MR1604428 0897.62035 10.1214/aos/1030741088 euclid.aos/1030741088
Devroye, L. and Lugosi, G. (1997). Nonasymptotic universal smoothing factors, kernel complexity and Yatracos classes. Ann. Statist. 25 2626–2637. MR1604428 0897.62035 10.1214/aos/1030741088 euclid.aos/1030741088
Devroye, L. and Lugosi, G. (2001). Combinatorial Methods in Density Estimation. Springer, New York. MR1843146 0964.62025Devroye, L. and Lugosi, G. (2001). Combinatorial Methods in Density Estimation. Springer, New York. MR1843146 0964.62025
Donoho, D. L., Johnstone, I. M., Kerkyacharian, G. and Picard, D. (1996). Density estimation by wavelet thresholding. Ann. Statist. 24 508–539. MR1394974 0860.62032 10.1214/aos/1032894451 euclid.aos/1032894451
Donoho, D. L., Johnstone, I. M., Kerkyacharian, G. and Picard, D. (1996). Density estimation by wavelet thresholding. Ann. Statist. 24 508–539. MR1394974 0860.62032 10.1214/aos/1032894451 euclid.aos/1032894451
Efromovich, S. Y. (2008). Adaptive estimation of and oracle inequalities for probability densities and characteristic functions. Ann. Statist. 36 1127–1155. MR2418652 05294968 10.1214/009053607000000965 euclid.aos/1211819559
Efromovich, S. Y. (2008). Adaptive estimation of and oracle inequalities for probability densities and characteristic functions. Ann. Statist. 36 1127–1155. MR2418652 05294968 10.1214/009053607000000965 euclid.aos/1211819559
Gach, D., Nickl, R. and Spokoiny, V. (2013). Spatially adaptive density estimation by localised Haar projections. Ann. Inst. Henri Poincaré Probab. Stat. To appear.Gach, D., Nickl, R. and Spokoiny, V. (2013). Spatially adaptive density estimation by localised Haar projections. Ann. Inst. Henri Poincaré Probab. Stat. To appear.
Giné, E. and Nickl, R. (2009). An exponential inequality for the distribution function of the kernel density estimator, with applications to adaptive estimation. Probab. Theory Related Fields 143 569–596. MR2475673 1160.62032 10.1007/s00440-008-0137-yGiné, E. and Nickl, R. (2009). An exponential inequality for the distribution function of the kernel density estimator, with applications to adaptive estimation. Probab. Theory Related Fields 143 569–596. MR2475673 1160.62032 10.1007/s00440-008-0137-y
Giné, E. and Nickl, R. (2010). Adaptive estimation of a distribution function and its density in sup-norm loss by wavelet and spline projections. Bernoulli 16 1137–1163. MR2759172 10.3150/09-BEJ239 euclid.bj/1290092899
Giné, E. and Nickl, R. (2010). Adaptive estimation of a distribution function and its density in sup-norm loss by wavelet and spline projections. Bernoulli 16 1137–1163. MR2759172 10.3150/09-BEJ239 euclid.bj/1290092899
Goldenshluger, A. and Lepski, O. (2008). Universal pointwise selection rule in multivariate function estimation. Bernoulli 14 1150–1190. MR2543590 10.3150/08-BEJ144 euclid.bj/1225980575
Goldenshluger, A. and Lepski, O. (2008). Universal pointwise selection rule in multivariate function estimation. Bernoulli 14 1150–1190. MR2543590 10.3150/08-BEJ144 euclid.bj/1225980575
Goldenshluger, A. and Lepski, O. (2009). Structural adaptation via $\mathbb{L}_{p}$-norm oracle inequalities. Probab. Theory Related Fields 143 41–71. MR2449122 1149.62020 10.1007/s00440-007-0119-5Goldenshluger, A. and Lepski, O. (2009). Structural adaptation via $\mathbb{L}_{p}$-norm oracle inequalities. Probab. Theory Related Fields 143 41–71. MR2449122 1149.62020 10.1007/s00440-007-0119-5
Goldenshluger, A. and Lepski, O. (2011). Bandwidth selection in kernel density estimation: Oracle inequalities and adaptive minimax optimality. Ann. Statist. 39 1608–1632. MR2850214 1234.62035 10.1214/11-AOS883 euclid.aos/1307452130
Goldenshluger, A. and Lepski, O. (2011). Bandwidth selection in kernel density estimation: Oracle inequalities and adaptive minimax optimality. Ann. Statist. 39 1608–1632. MR2850214 1234.62035 10.1214/11-AOS883 euclid.aos/1307452130
Goldenshluger, A. and Lepski, O. (2012). On adaptive minimax density estimation on $\mathbb{R}^{d}$. Available at arXiv:1210.1715v1. 1210.1715v1Goldenshluger, A. and Lepski, O. (2012). On adaptive minimax density estimation on $\mathbb{R}^{d}$. Available at arXiv:1210.1715v1. 1210.1715v1
Khasminskii, R. and Ibragimov, I. (1990). On density estimation in the view of Kolmogorov’s ideas in approximation theory. Ann. Statist. 18 999–1010. MR1062695 0705.62039 10.1214/aos/1176347736 euclid.aos/1176347736
Khasminskii, R. and Ibragimov, I. (1990). On density estimation in the view of Kolmogorov’s ideas in approximation theory. Ann. Statist. 18 999–1010. MR1062695 0705.62039 10.1214/aos/1176347736 euclid.aos/1176347736
Ibragimov, I. A. and Khasminskii, R. Z. (1980). An estimate of the density of a distribution. Zap. Nauchn. Sem. Leningrad. Otdel. Mat. Inst. Steklov. (LOMI) 98 61–85, 161–162, 166. MR591862Ibragimov, I. A. and Khasminskii, R. Z. (1980). An estimate of the density of a distribution. Zap. Nauchn. Sem. Leningrad. Otdel. Mat. Inst. Steklov. (LOMI) 98 61–85, 161–162, 166. MR591862
Ibragimov, I. A. and Khasminskii, R. Z. (1981). More on estimation of the density of a distribution. Zap. Nauchn. Sem. Leningrad. Otdel. Mat. Inst. Steklov. (LOMI) 108 72–88, 194, 198. MR629401Ibragimov, I. A. and Khasminskii, R. Z. (1981). More on estimation of the density of a distribution. Zap. Nauchn. Sem. Leningrad. Otdel. Mat. Inst. Steklov. (LOMI) 108 72–88, 194, 198. MR629401
Jennrich, R. I. (1969). Asymptotic properties of non-linear least squares estimators. Ann. Math. Statist. 40 633–643. MR238419 0193.47201 10.1214/aoms/1177697731 euclid.aoms/1177697731
Jennrich, R. I. (1969). Asymptotic properties of non-linear least squares estimators. Ann. Math. Statist. 40 633–643. MR238419 0193.47201 10.1214/aoms/1177697731 euclid.aoms/1177697731
Juditsky, A. and Lambert-Lacroix, S. (2004). On minimax density estimation on $\mathbb{R}$. Bernoulli 10 187–220. MR2046772 10.3150/bj/1082380217 euclid.bj/1082380217
Juditsky, A. and Lambert-Lacroix, S. (2004). On minimax density estimation on $\mathbb{R}$. Bernoulli 10 187–220. MR2046772 10.3150/bj/1082380217 euclid.bj/1082380217
Kerkyacharian, G., Lepski, O. and Picard, D. (2001). Nonlinear estimation in anisotropic multi-index denoising. Probab. Theory Related Fields 121 137–170. MR1863916 1010.62029 10.1007/PL00008800Kerkyacharian, G., Lepski, O. and Picard, D. (2001). Nonlinear estimation in anisotropic multi-index denoising. Probab. Theory Related Fields 121 137–170. MR1863916 1010.62029 10.1007/PL00008800
Kerkyacharian, G., Lepski, O. and Picard, D. (2007). Nonlinear estimation in anisotropic multiindex denoising. Sparse case. Theory Probab. Appl. 52 150–171. MR2354574 10.4213/tvp9Kerkyacharian, G., Lepski, O. and Picard, D. (2007). Nonlinear estimation in anisotropic multiindex denoising. Sparse case. Theory Probab. Appl. 52 150–171. MR2354574 10.4213/tvp9
Kerkyacharian, G., Picard, D. and Tribouley, K. (1996). $L^{p}$ adaptive density estimation. Bernoulli 2 229–247. MR1416864 euclid.bj/1178291720
Kerkyacharian, G., Picard, D. and Tribouley, K. (1996). $L^{p}$ adaptive density estimation. Bernoulli 2 229–247. MR1416864 euclid.bj/1178291720
Lepski, O. (2012). Upper functions for positive random functionals. Available at arXiv:1202.6615v1. 1202.6615v1Lepski, O. (2012). Upper functions for positive random functionals. Available at arXiv:1202.6615v1. 1202.6615v1
Lepski, O. V. and Levit, B. Y. (1999). Adaptive nonparametric estimation of smooth multivariate functions. Math. Methods Statist. 8 344–370. MR1735470 1104.62312Lepski, O. V. and Levit, B. Y. (1999). Adaptive nonparametric estimation of smooth multivariate functions. Math. Methods Statist. 8 344–370. MR1735470 1104.62312
Lepskiĭ, O. V. (1991). Asymptotically minimax adaptive estimation. I. Upper bounds. Optimally adaptive estimates. Theory Probab. Appl. 36 682–697. MR1147167Lepskiĭ, O. V. (1991). Asymptotically minimax adaptive estimation. I. Upper bounds. Optimally adaptive estimates. Theory Probab. Appl. 36 682–697. MR1147167
Lepskiĭ, O. V. (1992). On problems of adaptive estimation in white Gaussian noise. In Topics in Nonparametric Estimation. Adv. Soviet Math. 12 87–106. Amer. Math. Soc., Providence, RI. MR1191692Lepskiĭ, O. V. (1992). On problems of adaptive estimation in white Gaussian noise. In Topics in Nonparametric Estimation. Adv. Soviet Math. 12 87–106. Amer. Math. Soc., Providence, RI. MR1191692
Mason, D. M. (2009). Risk bounds for kernel density estimators. Zap. Nauchn. Sem. S.-Peterburg. Otdel. Mat. Inst. Steklov. (POMI) 363 66–104, 183. MR2749118Mason, D. M. (2009). Risk bounds for kernel density estimators. Zap. Nauchn. Sem. S.-Peterburg. Otdel. Mat. Inst. Steklov. (POMI) 363 66–104, 183. MR2749118
Massart, P. (2007). Concentration Inequalities and Model Selection. Lecture Notes in Math. 1896. Springer, Berlin. MR2319879 1170.60006Massart, P. (2007). Concentration Inequalities and Model Selection. Lecture Notes in Math. 1896. Springer, Berlin. MR2319879 1170.60006
Parzen, E. (1962). On estimation of a probability density function and mode. Ann. Math. Statist. 33 1065–1076. MR143282 0116.11302 10.1214/aoms/1177704472 euclid.aoms/1177704472
Parzen, E. (1962). On estimation of a probability density function and mode. Ann. Math. Statist. 33 1065–1076. MR143282 0116.11302 10.1214/aoms/1177704472 euclid.aoms/1177704472
Reynaud-Bouret, P., Rivoirard, V. and Tuleau-Malot, C. (2011). Adaptive density estimation: A curse of support? J. Statist. Plann. Inference 141 115–139. MR2719482 1197.62033 10.1016/j.jspi.2010.05.017Reynaud-Bouret, P., Rivoirard, V. and Tuleau-Malot, C. (2011). Adaptive density estimation: A curse of support? J. Statist. Plann. Inference 141 115–139. MR2719482 1197.62033 10.1016/j.jspi.2010.05.017
Rigollet, P. (2006). Adaptive density estimation using the blockwise Stein method. Bernoulli 12 351–370. MR2218559 10.3150/bj/1145993978 euclid.bj/1145993978
Rigollet, P. (2006). Adaptive density estimation using the blockwise Stein method. Bernoulli 12 351–370. MR2218559 10.3150/bj/1145993978 euclid.bj/1145993978
Rigollet, P. and Tsybakov, A. B. (2007). Linear and convex aggregation of density estimators. Math. Methods Statist. 16 260–280. MR2356821 1231.62057 10.3103/S1066530707030052Rigollet, P. and Tsybakov, A. B. (2007). Linear and convex aggregation of density estimators. Math. Methods Statist. 16 260–280. MR2356821 1231.62057 10.3103/S1066530707030052
Rosenblatt, M. (1956). Remarks on some nonparametric estimates of a density function. Ann. Math. Statist. 27 832–837. MR79873 0073.14602 10.1214/aoms/1177728190 euclid.aoms/1177728190
Rosenblatt, M. (1956). Remarks on some nonparametric estimates of a density function. Ann. Math. Statist. 27 832–837. MR79873 0073.14602 10.1214/aoms/1177728190 euclid.aoms/1177728190
Samarov, A. and Tsybakov, A. (2007). Aggregation of density estimators and dimension reduction. In Advances in Statistical Modeling and Inference. Ser. Biostat. 3 233–251. World Sci. Publ., Hackensack, NJ. MR2416118Samarov, A. and Tsybakov, A. (2007). Aggregation of density estimators and dimension reduction. In Advances in Statistical Modeling and Inference. Ser. Biostat. 3 233–251. World Sci. Publ., Hackensack, NJ. MR2416118
Tsybakov, A. B. (1998). Pointwise and sup-norm sharp adaptive estimation of functions on the Sobolev classes. Ann. Statist. 26 2420–2469. MR1700239 0933.62028 10.1214/aos/1024691478 euclid.aos/1024691478
Tsybakov, A. B. (1998). Pointwise and sup-norm sharp adaptive estimation of functions on the Sobolev classes. Ann. Statist. 26 2420–2469. MR1700239 0933.62028 10.1214/aos/1024691478 euclid.aos/1024691478