Convergence rates for the Bayesian approach to linear inverse problems∗
نویسندگان
چکیده
Recently, the metrics of Ky Fan and Prokhorov were introduced as a tool for studying convergence in stochastic ill-posed problems. In this work, we show that the Bayesian approach to linear inverse problems can be examined in the new framework as well. We consider the finitedimensional case where the measurements are disturbed by an additive normal noise and the prior distribution is normal. Convergence and convergence rate results are obtained when the covariance matrices are proportional to the identity matrix.
منابع مشابه
Convergence results for the Bayesian inversion theory∗
In this paper we derive convergence results for regularized solutions of linear inverse problems obtained by the Bayesian approach in the Ky Fan metric. We show that the convergence rate is order optimal in finite dimensional spaces. Moreover, we prove that order optimal rates can be obtained for weighted Bayesian solutions when the dimension goes to infinity.
متن کاملA New Inexact Inverse Subspace Iteration for Generalized Eigenvalue Problems
In this paper, we represent an inexact inverse subspace iteration method for computing a few eigenpairs of the generalized eigenvalue problem Ax = Bx [Q. Ye and P. Zhang, Inexact inverse subspace iteration for generalized eigenvalue problems, Linear Algebra and its Application, 434 (2011) 1697-1715 ]. In particular, the linear convergence property of the inverse subspace iteration is preserved.
متن کاملModify the linear search formula in the BFGS method to achieve global convergence.
<span style="color: #333333; font-family: Calibri, sans-serif; font-size: 13.3333px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: justify; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: #ffffff; text-dec...
متن کاملConvergence rates for linear inverse problems in the presence of an additive normal noise∗
In this work, we examine a finite-dimensional linear inverse problem where the measurements are disturbed by an additive normal noise. The problem is solved both in the frequentist and in the Bayesian frameworks. Convergence of the used methods when the noise tends to zero is studied in the Ky Fan metric. The obtained convergence rate results and parameter choice rules are of a similar structur...
متن کاملConsistency and efficiency of Bayesian estimators in generalised linear inverse problems
Formulating a statistical inverse problem as one of inference in a Bayesian model has great appeal, notably for what this brings in terms of coherence, the interpretability of regularisation penalties, the integration of all uncertainties, and the principled way in which the set-up can be elaborated to encompass broader features of the context, such as measurement error, indirect observation, e...
متن کامل