We give a new approach to the dictionary learning (also known as "sparse coding") problem of recovering an unknown n x m matrix A (for m ≥ n) from examples of the form [y = Ax + e,] where x is a random vector in R<sup>m</sup> with at most τ m nonzero coordinates, and e is a random noise vector in R<sup>n</sup> with bounded magnitude. For the case… (More)