Posterior consistency and convergence rates for Bayesian inversion with hypoelliptic operators

Bayesian approach to inverse problems is studied in the case where the forward map is a linear hypoelliptic pseudodifferential operator and measurement error is additive white Gaussian noise. The measurement model for an unknown Gaussian random variable $U(x,\omega)$ is \begin{eqnarray*} M(y,\omega) = A(U(x,\omega) )+ \delta\hspace{.2mm}\mathcal{E}(y,\omega), \end{eqnarray*} where $A$ is a finitely many times smoothing linear hypoelliptic operator and $\delta>0$ is the noise magnitude. The covariance operator $C_U$ of $U$ is $2r$ times smoothing, self-adjoint, injective and elliptic pseudodifferential operator. If $\mathcal{E}$ was taking values in $L^2$ then in Gaussian case solving the conditional mean (and maximum a posteriori) estimate is linked to solving the minimisation problem \begin{eqnarray*} T_\delta(M) = \text{argmin}_{u\in H^r} \big\{\|A u-m\|_{L^2}^2+ \delta^2\|C_U^{-1/2}u\|_{L^2}^2 \big\}. \end{eqnarray*} However, Gaussian white noise does not take values in $L^2$ but in $H^{-s}$ where $s>0$ is big enough. A modification of the above approach to solve the inverse problem is presented, covering the case of white Gaussian measurement noise. Furthermore, the convergence of conditional mean estimate to the correct solution as $\delta\rightarrow 0$ is proven in appropriate function spaces using microlocal analysis. Also the contraction of the confidence regions is studied.

[1]  Sari Lasanen,et al.  Non-Gaussian statistical inverse problems. Part I: Posterior distributions , 2012 .

[2]  H. Leahu On the Bernstein-von Mises phenomenon in the Gaussian white noise model , 2011 .

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

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

[5]  S. Siltanen,et al.  Can one use total variation prior for edge-preserving Bayesian inversion? , 2004 .

[6]  L. Hörmander The Analysis of Linear Partial Differential Operators III , 2007 .

[7]  A. Tikhonov,et al.  Numerical Methods for the Solution of Ill-Posed Problems , 1995 .

[8]  Barbara Kaltenbacher,et al.  Regularization Methods in Banach Spaces , 2012, Radon Series on Computational and Applied Mathematics.

[9]  A Tikhonov,et al.  Solution of Incorrectly Formulated Problems and the Regularization Method , 1963 .

[10]  W. Rudin Real and complex analysis , 1968 .

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

[12]  Anna Simoni,et al.  REGULARIZING PRIORS FOR LINEAR INVERSE PROBLEMS , 2014, Econometric Theory.

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

[14]  M. Shubin Pseudodifferential Operators and Spectral Theory , 1987 .

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

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

[17]  R. Nickl,et al.  On the Bernstein–von Mises phenomenon for nonparametric Bayes procedures , 2013, 1310.2484.

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

[19]  Erkki Somersalo,et al.  Linear inverse problems for generalised random variables , 1989 .

[20]  Kolyan Ray Adaptive Bernstein–von Mises theorems in Gaussian white noise , 2014, 1407.3397.

[21]  Matti Lassas. Eero Saksman,et al.  Discretization-invariant Bayesian inversion and Besov space priors , 2009, 0901.4220.

[22]  Dudley,et al.  Real Analysis and Probability: Measurability: Borel Isomorphism and Analytic Sets , 2002 .

[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]  C. W. Groetsch,et al.  The theory of Tikhonov regularization for Fredholm equations of the first kind , 1984 .

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

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

[27]  O. Kallenberg Foundations of Modern Probability , 2021, Probability Theory and Stochastic Modelling.

[28]  A. Pascucci PDE and Martingale Methods in Option Pricing , 2010 .

[29]  Subhashis Ghosal,et al.  A Review of Consistency and Convergence of Posterior Distribution , 2022 .

[30]  Matti Lassas,et al.  Analysis of regularized inversion of data corrupted by white Gaussian noise , 2013, 1311.6323.

[31]  L. Hörmander The analysis of linear partial differential operators , 1990 .

[32]  I. Rozanov,et al.  Infinite-dimensional Gaussian distributions , 1971 .

[33]  V. Bogachev Gaussian Measures on a , 2022 .

[34]  B. Knapik,et al.  A general approach to posterior contraction in nonparametric inverse problems , 2014, Bernoulli.

[35]  R. M. Dudley,et al.  Real Analysis and Probability , 1989 .

[36]  G. Folland Compact Heisenberg manifolds as CR manifolds , 2004 .

[37]  H. B. Mitchell Markov Random Fields , 1982 .

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

[39]  Harry van Zanten,et al.  Honest Bayesian confidence sets for the L2-norm , 2013, 1311.7474.

[40]  Ben G. Fitzpatrick,et al.  Bayesian analysis in inverse problems , 1991 .

[41]  C. Atkinson METHODS FOR SOLVING INCORRECTLY POSED PROBLEMS , 1985 .

[42]  A. Mandelbaum,et al.  Linear estimators and measurable linear transformations on a Hilbert space , 1984 .

[43]  R. Nickl,et al.  Nonparametric Bernstein–von Mises theorems in Gaussian white noise , 2012, 1208.3862.

[44]  F. Nier,et al.  Hypoelliptic Estimates and Spectral Theory for Fokker-Planck Operators and Witten Laplacians , 2005 .

[45]  David L. Phillips,et al.  A Technique for the Numerical Solution of Certain Integral Equations of the First Kind , 1962, JACM.

[46]  L. Hörmander Hypoelliptic second order differential equations , 1967 .

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

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

[49]  A. Tikhonov On the stability of inverse problems , 1943 .

[50]  Andrew M. Stuart,et al.  Inverse problems: A Bayesian perspective , 2010, Acta Numerica.

[51]  A. Kolmogoroff,et al.  Zufallige Bewegungen (Zur Theorie der Brownschen Bewegung) , 1934 .

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

[53]  A. Stuart,et al.  MAP estimators and their consistency in Bayesian nonparametric inverse problems , 2013, 1303.4795.

[54]  Y. Rozanov,et al.  Markov random fields , 1984 .

[55]  E. Somersalo,et al.  Statistical and computational inverse problems , 2004 .

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

[57]  V. Kolehmainen,et al.  Sparsity-promoting Bayesian inversion , 2012 .

[58]  A. Kirsch An Introduction to the Mathematical Theory of Inverse Problems , 1996, Applied Mathematical Sciences.