Analysis of a low memory implementation of the Orthogonal Matching Pursuit greedy strategy

The convergence and numerical analysis of a low memory implementation of the Orthogonal Matching Pursuit greedy strategy, which is termed Self Projected Matching Pursuit, is presented. This approach provides an iterative way of solving the least squares problem with much less storage requirement than direct linear algebra techniques. Hence, it is appropriate for solving large linear systems. Furthermore, the low memory requirement of the method suits it for massive parallelization, via Graphics Processing Unit, to tackle systems which can be broken into a large number of subsystems of much smaller dimension.