Maximum Likelihood Estimation of Regularization Parameters in High-Dimensional Inverse Problems: An Empirical Bayesian Approach Part I: Methodology and Experiments.
Ana Fernandez VidalValentin De BortoliMarcelo PereyraAlain DurmusPublished in: SIAM J. Imaging Sci. (2020)
Keyphrases
- maximum likelihood estimation
- inverse problems
- regularization method
- regularization parameter
- high dimensional
- em algorithm
- image reconstruction
- global optimization
- maximum likelihood
- hyperparameters
- convex optimization
- expectation maximization
- image restoration
- parameter estimation
- probability distribution
- optimization methods
- parameter space
- early vision
- dimensionality reduction
- high dimensional data
- cross validation
- low dimensional
- optimization problems
- density function
- smoothness constraint
- partial differential equations
- computer vision
- generative model
- data points
- multiscale
- maximum a posteriori
- gaussian noise
- high quality