Distributed SAGA: Maintaining linear convergence rate with limited communication

@article{Calauznes2017DistributedSM,
  title={Distributed SAGA: Maintaining linear convergence rate with limited communication},
  author={Cl{\'e}ment Calauz{\`e}nes and Nicolas Le Roux},
  journal={CoRR},
  year={2017},
  volume={abs/1705.10405}
}
In recent years, variance-reducing stochastic methods have shown great practical performance, exhibiting linear convergence rate when other stochastic methods offered a sub-linear rate. However, as datasets grow ever bigger and clusters become widespread, the need for fast distribution methods is pressing. We propose here a distribution scheme for SAGA… CONTINUE READING