TY  - CONF
AV  - none
M2  - Los Angeles, CA
ID  - eprints2971
TI  - Douglas-rachford splitting: Complexity estimates and accelerated variants
UR  - http://dx.doi.org/10.1109/CDC.2014.7040049
KW  - computational complexity;convergence;convex programming;gradient methods;DRE;DRS;Douglas-Rachford envelope;Douglas-Rachford splitting method;accelerated variants;complexity estimates;continuously differentiable function;convergence properties;convex composite optimization problems;scaled gradient method;smooth unconstrained optimization;Acceleration;Complexity theory;Convergence;Convex functions;Gradient methods;Radio frequency
N2  - We propose a new approach for analyzing convergence of the Douglas-Rachford splitting method for solving convex composite optimization problems. The approach is based on a continuously differentiable function, the Douglas-Rachford Envelope (DRE), whose stationary points correspond to the solutions of the original (possibly nonsmooth) problem. By proving the equivalence between the Douglas-Rachford splitting method and a scaled gradient method applied to the DRE, results from smooth unconstrained optimization are employed to analyze convergence properties of DRS, to tune the method and to derive an accelerated version of it.
SN  - 978-1-4799-7746-8
EP  - 4239
PB  - IEEE
Y1  - 2014/12//
SP  - 4234
T2  - IEEE 53rd Annual Conference on Decision and Control (CDC), 2014
A1  - Patrinos, Panagiotis
A1  - Stella, Lorenzo
A1  - Bemporad, Alberto
ER  -