Combining fast inertial dynamics for convex optimization with Tikhonov regularization
Abstract
In a Hilbert space setting , we study the convergence properties as of the trajectories of the second-order differential equation \begin{equation*} \mbox{(AVD)}_{\alpha, \epsilon} \quad \quad \ddot{x}(t) + \frac{\alpha}{t} \dot{x}(t) + \nabla \Phi (x(t)) + \epsilon (t) x(t) =0, \end{equation*} where is the gradient of a convex continuously differentiable function , is a positive parameter, and is a Tikhonov regularization term, with . In this damped inertial system, the damping coefficient vanishes asymptotically, but not too quickly, a key property to obtain rapid convergence of the values. In the case , this dynamic has been highlighted recently by Su, Boyd, and Cand\`es as a continuous version of the Nesterov accelerated method. Depending on the speed of convergence of to zero, we analyze the convergence properties of the trajectories of . We obtain results ranging from the rapid convergence of to when decreases rapidly to zero, up to the strong ergodic convergence of the trajectories to the element of minimal norm of the set of minimizers of , when tends slowly to zero.
Cite
@article{arxiv.1602.01973,
title = {Combining fast inertial dynamics for convex optimization with Tikhonov regularization},
author = {Hedy Attouch and Zaki Chbani},
journal= {arXiv preprint arXiv:1602.01973},
year = {2016}
}