In this paper, we study convergence and efficiency of the batch estimator and natural gradient algorithm for blind deconvolution. First, the blind deconvolution problem is formulated in the framework of a semiparametric model, and a family of estimating functions is derived for blind deconvolution. To improve the learning efficiency of the online algorithm, explicit standardized estimating functions are given and within this framework the superefficiency of batch learning and online natural gradient learning is proven.
- Blind deconvolution
- Estimating function
- Independent component analysis
- Natural gradient
- Semiparametric model