On the Proximal Gradient Algorithm with Alternated Inertia

01/17/2018
by   Franck Iutzeler, et al.
0

In this paper, we investigate the attractive properties of the proximal gradient algorithm with inertia. Notably, we show that using alternated inertia yields monotonically decreasing functional values, which contrasts with usual accelerated proximal gradient methods. We also provide convergence rates for the algorithm with alternated inertia based on local geometric properties of the objective function. The results are put into perspective by discussions on several extensions and illustrations on common regularized problems.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset