A general approach to posterior contraction in nonparametric inverse problems

In this paper we propose a general method to derive an upper bound for the contraction rate of the posterior distribution for nonparametric inverse problems. We present a general theorem that allows us to derive con- traction rates for the parameter of interest from contraction rates of the related direct problem of estimating transformed parameter of interest. An interesting aspect of this approach is that it allows us to derive con- traction rates for priors that are not related to the singular value decomposition of the operator. We apply our result to several examples of linear inverse problems, both in the white noise sequence model and the nonparametric regression model, using priors based on the singular value decomposition of the operator, location-mixture priors and splines prior, and recover minimax adaptive contraction rates.

[1]  Judith Rousseau,et al.  On adaptive posterior concentration rates , 2013, 1305.5270.

[2]  Alexander Meister.  Asymptotic equivalence of functional linear regression and a white noise inverse problem , 2011 .

[3]  L. Cavalier.  Nonparametric statistical inverse problems , 2008 .

[4]  Botond Szabo,et al.  Bayes procedures for adaptive inference in nonparametric inverse problems , 2012 .

[5]  A. V. D. Vaart,et al.  Convergence rates of posterior distributions , 2000 .

[6]  S. Ghosal,et al.  Adaptive Bayesian multivariate density estimation with Dirichlet mixtures , 2011, 1109.6406.

[7]  A. W. Vaart,et al.  Bayes procedures for adaptive inference in inverse problems for the white noise model , 2012, Probability Theory and Related Fields.

[8]  D. Donoho,et al.  Geometrizing Rates of Convergence , II , 2008 .

[9]  Catia Scricciolo.  Adaptive Bayesian Density Estimation in $L^{p}$-metrics with Pitman-Yor or Normalized Inverse-Gaussian Process Kernel Mixtures , 2014 .

[10]  E. Belitser,et al.  Adaptive Bayesian inference on the mean of an infinite-dimensional normal distribution , 2003 .

[11]  Grace L. Yang,et al.  On Bayes Procedures , 1990 .

[12]  L. Brown,et al.  Asymptotic equivalence of nonparametric regression and white noise , 1996 .

[13]  MCMC-free adaptive Bayesian procedures using random series prior , 2012, 1204.4238.

[14]  J. Florens,et al.  Regularized Posteriors in Linear Ill‐Posed Inverse Problems , 2012 .

[15]  H. Engl,et al.  Regularization of Inverse Problems , 1996 .

[16]  J. Rousseau.  Rates of convergence for the posterior distributions of mixtures of betas and adaptive nonparamatric estimation of the density , 2010, 1001.1615.

[17]  J. Salomond.  Concentration rate and consistency of the posterior distribution for selected priors under monotonicity constraints , 2013, 1301.1898.

[18]  Linda H. Zhao.  Bayesian aspects of some nonparametric problems , 2000 .

[19]  A. W. Vaart,et al.  Frequentist coverage of adaptive nonparametric Bayesian credible sets , 2013, 1310.4489.

[20]  J. H. Zanten,et al.  Adaptive nonparametric Bayesian inference using location-scale mixture priors , 2010, 1211.2121.

[21]  Judith Rousseau,et al.  Posterior concentration rates for empirical Bayes procedures, with applications to Dirichlet Process mixtures , 2014, 1406.4406.

[22]  Anna Simoni,et al.  Nonparametric Estimation of An Instrumental Regression: A Quasi-Bayesian Approach Based on Regularized Posterior , 2012 .

[23]  A. V. D. Vaart,et al.  Entropies and rates of convergence for maximum likelihood and Bayes estimation for mixtures of normal densities , 2001 .

[24]  D. Donoho,et al.  Geometrizing Rates of Convergence, III , 1991 .

[25]  A. V. D. Vaart,et al.  Needles and Straw in a Haystack: Posterior concentration for possibly sparse sequences , 2012, 1211.1197.

[26]  Jianqing Fan.  On the Optimal Rates of Convergence for Nonparametric Deconvolution Problems , 1991 .

[27]  A. W. van der Vaart,et al.  Bayesian Recovery of the Initial Condition for the Heat Equation , 2011, 1111.5876.

[28]  A. V. D. Vaart,et al.  BAYESIAN INVERSE PROBLEMS WITH GAUSSIAN PRIORS , 2011, 1103.2692.

[29]  C. R. Deboor,et al.  A practical guide to splines , 1978 .

[30]  J. Ghosh,et al.  POSTERIOR CONSISTENCY OF DIRICHLET MIXTURES IN DENSITY ESTIMATION , 1999 .

[31]  K. Mengersen,et al.  Asymptotic behaviour of the posterior distribution in overfitted mixture models , 2011 .

[32]  A. V. D. Vaart,et al.  Adaptive Bayesian density estimation with location-scale mixtures , 2010 .

[33]  S. Ghosal,et al.  Adaptive Bayesian Procedures Using Random Series Priors , 2014, 1403.0625.

[34]  Stig Larsson,et al.  Posterior Contraction Rates for the Bayesian Approach to Linear Ill-Posed Inverse Problems , 2012, 1203.5753.

[35]  A. V. D. Vaart,et al.  BAYESIAN LINEAR REGRESSION WITH SPARSE PRIORS , 2014, 1403.0735.

[36]  Judith Rousseau,et al.  Bayesian Optimal Adaptive Estimation Using a Sieve Prior , 2012, 1204.2392.

[37]  L. Wasserman,et al.  Rates of convergence of posterior distributions , 2001 .

[38]  M. Nussbaum.  Asymptotic Equivalence of Density Estimation and Gaussian White Noise , 1996 .

[39]  A. V. D. Vaart,et al.  Convergence rates of posterior distributions for non-i.i.d. observations , 2007, 0708.0491.

[40]  Eduard Belitser.  On coverage and local radial rates of credible sets , 2017 .

[41]  de R René Jonge,et al.  Adaptive estimation of multivariate functions using conditionally Gaussian tensor-product spline priors , 2012 .

[42]  Kolyan Ray,et al.  Bayesian inverse problems with non-conjugate priors , 2012, 1209.6156.

[43]  R. Cooke.  Real and Complex Analysis , 2011 .

[44]  Andrew M. Stuart,et al.  Bayesian posterior contraction rates for linear severely ill-posed inverse problems , 2012, 1210.1563.

[45]  L. Wasserman,et al.  The consistency of posterior distributions in nonparametric problems , 1999 .

[46]  I. Castillo.  On Bayesian supremum norm contraction rates , 2013, 1304.1761.

[47]  S. Vollmer,et al.  Posterior consistency for Bayesian inverse problems through stability and regression results , 2013, 1302.4101.

[48]  S. Ghosal,et al.  Adaptive Bayesian procedures using random series prior , 2012 .