Modified Fejér sequences and applications
Author(s)Lin, Junhong; Rosasco, Lorenzo; Villa, Silvia; Zhou, Ding-Xuan
MetadataShow full item record
In this note, we propose and study the notion of modified Fejér sequences. Within a Hilbert space setting, this property has been used to prove ergodic convergence of proximal incremental subgradient methods. Here we show that indeed it provides a unifying framework to prove convergence rates for objective function values of several optimization algorithms. In particular, our results apply to forward–backward splitting algorithm, incremental subgradient proximal algorithm, and the Douglas–Rachford splitting method including and generalizing known results.
DepartmentMassachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Computational Optimization and Applications
Lin, Junhong, et al. “Modified Fejér Sequences and Applications.” Computational Optimization and Applications, vol. 71, no. 1, Sept. 2018, pp. 95–113.
Author's final manuscript