Cost free hyper-parameter selection/averaging for Bayesian inverse problems with vanilla and Rao-Blackwellized SMC samplers.
Alessandro VianiAdam M. JohansenAlberto SorrentinoPublished in: Stat. Comput. (2023)
Keyphrases
- inverse problems
- hyperparameters
- bayesian inference
- random sampling
- image reconstruction
- global optimization
- convex optimization
- model selection
- maximum likelihood
- probabilistic model
- optimization problems
- optimization methods
- prior information
- closed form
- cross validation
- optimization algorithm
- partial differential equations
- machine learning
- sample size
- incremental learning
- natural images
- particle filter
- computational complexity
- support vector
- bayesian networks
- early vision
- high quality