A unified Laplace approximation error bound with a tunable matrix D recovers prior bounds and yields an order-of-magnitude tighter, dimension-free estimate in a Bayesian inverse problem.
On the Bernstein-Von Mises Theorem for High Dimensional Nonlinear Bayesian Inverse Problems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We prove a Bernstein-von Mises theorem for a general class of high dimensional nonlinear Bayesian inverse problems in the vanishing noise limit. We propose a sufficient condition on the growth rate of the number of unknown parameters under which the posterior distribution is asymptotically normal. This growth condition is expressed explicitly in terms of the model dimension, the degree of ill-posedness of the inverse problem and the noise parameter. The theoretical results are applied to a Bayesian estimation of the medium parameter in an elliptic problem.
fields
math.ST 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A unified theory of the high-dimensional Laplace approximation with application to Bayesian inverse problems
A unified Laplace approximation error bound with a tunable matrix D recovers prior bounds and yields an order-of-magnitude tighter, dimension-free estimate in a Bayesian inverse problem.