Abstract
Recently, sparse coding has been widely used in many ap- plications ranging from image recovery to pattern recognition. The low mutual coherence of a dictionary is an important property that ensures the optimality of the sparse code generated from this dictionary. Indeed, most existing dictionary learning methods for sparse coding either implic- itly or explicitly tried to learn an incoherent dictionary, which requires solving a very challenging non-convex optimization problem. In this pa- per, we proposed a hybrid alternating proximal algorithm for incoher- ent dictionary learning, and established its global convergence property. Such a convergent incoherent dictionary learning method is not only of theoretical interest, but also might benefit many sparse coding based applications.