Bayesian inverse problems with non-conjugate priors

We investigate the frequentist posterior contraction rate of nonparametric Bayesian procedures in linear inverse problems in both the mildly and severely ill-posed cases. A theorem is proved in a general Hilbert space setting under approximation-theoretic assumptions on the prior. The result is applied to non-conjugate priors, notably sieve and wavelet series priors, as well as in the conjugate setting. In the mildly ill-posed setting minimax optimal rates are obtained, with sieve priors being rate adaptive over Sobolev classes. In the severely ill-posed setting, oversmoothing the prior yields minimax rates. Previously established results in the conjugate setting are obtained using this method. Examples of applications include deconvolution, recovering the initial condition in the heat equation and the Radon transform.

[1]  Gerard Kerkyacharian,et al.  Thomas Bayes’ walk on manifolds , 2012, 1206.0459.

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

[3]  Van Der Vaart,et al.  Adaptive Bayesian estimation using a Gaussian random field with inverse Gamma bandwidth , 2009, 0908.3556.

[4]  R. Nickl,et al.  GLOBAL UNIFORM RISK BOUNDS FOR WAVELET DECONVOLUTION ESTIMATORS , 2011, 1103.1489.

[5]  Richard Nickl,et al.  Rates of contraction for posterior distributions in Lr-metrics, 1 ≤ r ≤ ∞ , 2011, 1203.2043.

[6]  Amir Dembo,et al.  Exact behavior of Gaussian seminorms , 1995 .

[7]  B. Vidakovic,et al.  Adaptive wavelet estimator for nonparametric density deconvolution , 1999 .

[8]  M. Ledoux.  The concentration of measure phenomenon , 2001 .

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

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

[11]  Bernard W. Silverman,et al.  Speed of Estimation in Positron Emission Tomography and Related Inverse Problems , 1990 .

[12]  Y. Meyer.  Wavelets and Operators , 1993 .

[13]  A. F. M. Smith,et al.  Bayesian Wavelet Analysis with a Model Complexity Prior , 1998 .

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

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

[16]  C. Borell.  The Brunn-Minkowski inequality in Gauss space , 1975 .

[17]  A. W. Vaart,et al.  Reproducing kernel Hilbert spaces of Gaussian priors , 2008, 0805.3252.

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

[19]  Tzee-Ming Huang.  Convergence rates for posterior distributions and adaptive estimation , 2004, math/0410087.

[20]  Cristina Butucea,et al.  Sharp Optimality in Density Deconvolution with Dominating Bias. II , 2008 .

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

[22]  M. Escobar,et al.  Markov Chain Sampling Methods for Dirichlet Process Mixture Models , 2000 .

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

[24]  Van Der Vaart,et al.  Rates of contraction of posterior distributions based on Gaussian process priors , 2008 .

[25]  Gerard Kerkyacharian,et al.  Wavelet deconvolution in a periodic setting , 2004 .

[26]  G. Prato.  An Introduction to Infinite-Dimensional Analysis , 2006 .

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

[28]  A. V. D. Vaart,et al.  Posterior convergence rates of Dirichlet mixtures at smooth densities , 2007, 0708.1885.

[29]  J. Kuelbs,et al.  Metric entropy and the small ball problem for Gaussian measures , 1993 .

[30]  Nicolai Bissantz,et al.  Convergence Rates of General Regularization Methods for Statistical Inverse Problems and Applications , 2007, SIAM J. Numer. Anal..

[31]  R. Dudley,et al.  On the Lower Tail of Gaussian Seminorms , 1979 .