Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval, Matrix Completion, and Blind Deconvolution.
Cong MaKaizheng WangYuejie ChiYuxin ChenPublished in: Found. Comput. Math. (2020)
Keyphrases
- blind deconvolution
- statistical estimation
- matrix completion
- total variation
- low rank
- convex optimization
- objective function
- image deblurring
- cost function
- blurred images
- image denoising
- multi frame
- convex relaxation
- stochastic gradient descent
- image segmentation
- image restoration
- point spread function
- alternating direction method of multipliers
- bayesian framework
- map estimation
- linear combination
- singular values
- denoising
- probabilistic model
- minimization problems
- loss function
- pairwise
- face recognition
- image processing
- computer vision