Bernstein--von Mises theorems for Bayesian probabilistic numerics (Q7285207)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
No description defined
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Bernstein--von Mises theorems for Bayesian probabilistic numerics |
No description defined |
Statements
Bernstein--von Mises theorems for Bayesian probabilistic numerics (English)
0 references
3 September 2026
0 references
math.ST
0 references
math.NA
0 references
Sascha Gaudlitz
0 references
Sven Wang
0 references
We derive Bernstein--von Mises theorems for Bayesian probabilistic numerics, showing contraction rates in strong topologies such as uniform and positive-order Sobolev spaces, with Gaussian approximations of the posterior that are asymptotically equivalent to the true posterior at a $\sqrt{N}$-scale.
0 references
Bayesian
0 references
Probabilistic Numerics
0 references
Nonparametric Bayesian Inference
0 references
Gaussian Approximations
0 references
Sobolev Spaces
0 references