On the convergence of the Laplace approximation and noise-level-robustness of Laplace-based Monte Carlo methods for Bayesian inverse problems.
Claudia SchillingsBjörn SprungkPhilipp WackerPublished in: Numerische Mathematik (2020)
Keyphrases
- monte carlo methods
- noise level
- inverse problems
- monte carlo
- noisy images
- bayesian networks
- image reconstruction
- global optimization
- noise reduction
- optimization methods
- simulated annealing
- hyperparameters
- convex optimization
- bayesian learning
- early vision
- monte carlo method
- computer vision
- higher order
- image processing