A subgradient method with constant step-size for \ell₁-composite optimization
From MaRDI portal
A subgradient method with constant step-size for $\ell 1$-composite optimization
Abstract: Subgradient methods are the natural extension to the non-smooth case of the classical gradient descent for regular convex optimization problems. However, in general, they are characterized by slow convergence rates, and they require decreasing step-sizes to converge. In this paper we propose a subgradient method with constant step-size for composite convex objectives with -regularization. If the smooth term is strongly convex, we can establish a linear convergence result for the function values. This fact relies on an accurate choice of the element of the subdifferential used for the update, and on proper actions adopted when non-differentiability regions are crossed. Then, we propose an accelerated version of the algorithm, based on conservative inertial dynamics and on an adaptive restart strategy. Finally, we test the performances of our algorithms on some strongly and non-strongly convex examples.
This page was built for publication: A subgradient method with constant step-size for $\ell_1$-composite optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6427424)
