Gradient-Based Methods for Sparse Recovery
Gradient-Based Methods for Sparse Recovery
The convergence rate is analyzed for the sparse reconstruction by separable approximation (SpaRSA) algorithm for minimizing a sum $f(\mathbf{x})+\psi(\mathbf{x})$, where f is smooth and $\psi$ is convex, but possibly nonsmooth. It is shown that if f is convex, then the error in the objective function at iteration k is bounded …