# Non-asymptotic error estimates for the Laplace approximation in Bayesian inverse problems

@article{Helin2020NonasymptoticEE, title={Non-asymptotic error estimates for the Laplace approximation in Bayesian inverse problems}, author={T. Helin and Remo Kretschmann}, journal={ArXiv}, year={2020}, volume={abs/2012.06603} }

In this paper we study properties of the Laplace approximation of the posterior distribution arising in nonlinear Bayesian inverse problems. Our work is motivated by Schillings et al. (2020), where it is shown that in such a setting the Laplace approximation error in Hellinger distance converges to zero in the order of the noise level. Here, we prove novel error estimates for a given noise level that also quantify the effect due to the nonlinearity of the forward mapping and the dimension of… Expand

#### Figures from this paper

#### One Citation

#### References

SHOWING 1-10 OF 27 REFERENCES

On the convergence of the Laplace approximation and noise-level-robustness of Laplace-based Monte Carlo methods for Bayesian inverse problems

- Mathematics, Computer Science
- Numerische Mathematik
- 2020

Multivariate Laplace's approximation with estimated error and application to limit theorems

- Mathematics, Computer Science
- J. Approx. Theory
- 2019

Hessian-based adaptive sparse quadrature for infinite-dimensional Bayesian inverse problems☆

- Mathematics
- 2017

On the Bernstein-Von Mises Theorem for High Dimensional Nonlinear Bayesian Inverse Problems

- Mathematics
- 2017

Fast estimation of expected information gains for Bayesian experimental designs based on Laplace approximations

- Mathematics
- 2013

Bernstein-von Mises Theorems and Uncertainty Quantification for Linear Inverse Problems

- Mathematics, Computer Science
- SIAM/ASA J. Uncertain. Quantification
- 2020

A Fast and Scalable Method for A-Optimal Design of Experiments for Infinite-dimensional Bayesian Nonlinear Inverse Problems

- Mathematics, Computer Science
- SIAM J. Sci. Comput.
- 2016