Super-Linear Convergence of Dual Augmented Lagrangian Algorithm for Sparse Learning

We analyze the convergence behaviour of a recently proposed algorithm for sparse learning called Dual Augmented Lagrangian (DAL). We theoretically analyze under some conditions that DAL converges super-linearly in a non-asymptotic and global sense. We experimentally confirm our analysis in a large scale $\ell_1$-regularized logistic regression problem and compare the efficiency of DAL algorithm to existing algorithms.