Efficient ADMM-Based Algorithms for Convolutional Sparse Coding

Convolutional sparse coding improves on the standard approximation by incorporating a global shift-invariant model. The most efficient convolutional methods are based alternating direction method of multipliers and convolution theorem. only major difference between these is how they approach least-squares fitting subproblem. This letter presents solution to this subproblem, which efficiency state-of-the-art algorithms. We also use same for developing an dictionary learning method. Furthermore, we propose novel algorithm with constraint error.