Bounded OS-DL: An improvement for one-stage dictionary learning algorithm

In this paper we propose a novel algorithm, which is an improvement for one-stage dictionary learning (OS-DL) algorithm, by imposing a l 2 -norm constraint on the update of the atoms. Our contribution embarks from the OS-DL algorithm and incorporates the well-known convex optimization method, proximal point method, into this algorithm. Experimental results on recovering a known dictionary and sparsely approximating an AR(1) signal demonstrate the promising performance of our proposed algorithm.