ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1811.04058
156
21
v1v2v3v4 (latest)

Bernstein-von Mises theorems and uncertainty quantification for linear inverse problems

9 November 2018
M. Giordano
Hanne Kekkonen
ArXiv (abs)PDFHTML
Abstract

We consider the statistical inverse problem of recovering an unknown function fff from a linear measurement corrupted by additive Gaussian white noise. We employ a nonparametric Bayesian approach with standard Gaussian priors, for which the posterior-based reconstruction of fff corresponds to a Tikhonov regulariser fˉ\bar ffˉ​ with a reproducing kernel Hilbert space norm penalty. We prove a semiparametric Bernstein-von Mises theorem for a large collection of linear functionals of fff, implying that semiparametric posterior estimation and uncertainty quantification are valid and optimal from a frequentist point of view. The result is applied to study three concrete examples that cover both the mildly and severely ill-posed cases: specifically, an elliptic inverse problem, an elliptic boundary value problem and the heat equation. For the elliptic boundary value problem, we also obtain a nonparametric version of the theorem that entails the convergence of the posterior distribution to a prior-independent infinite-dimensional Gaussian probability measure with minimal covariance. As a consequence, it follows that the Tikhonov regulariser fˉ\bar ffˉ​ is an efficient estimator of fff, and we derive frequentist guarantees for certain credible balls centred at fˉ\bar{f}fˉ​.

View on arXiv
Comments on this paper