Asynchronous Stochastic Coordinate Descent: Parallelism and Convergence Properties

@article{Liu2014AsynchronousSC,
  title={Asynchronous Stochastic Coordinate Descent: Parallelism and Convergence Properties},
  author={Ji Liu and Stephen J. Wright},
  journal={SIAM Journal on Optimization},
  year={2014},
  volume={25},
  pages={351-376}
}
We describe an asynchronous parallel stochastic proximal coordinate descent algorithm for minimizing a composite objective function, which consists of a smooth convex function plus a separable convex function. In contrast to previous analyses, our model of asynchronous computation accounts for the fact that components of the unknown vector may be written by some cores simultaneously with being read by others. Despite the complications arising from this possibility, the method achieves a linear… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 158 CITATIONS

Asynchronous parallel nonconvex large-scale optimization

  • 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2017
VIEW 15 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED

Asynchronous Doubly Stochastic Proximal Optimization with Variance Reduction

VIEW 35 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Asynchronous Stochastic Block Coordinate Descent with Variance Reduction

VIEW 15 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Parallel asynchronous lock-free algorithms for nonconvex big-data optimization

  • 2016 50th Asilomar Conference on Signals, Systems and Computers
  • 2016
VIEW 8 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Coordinate descent algorithms

  • Math. Program.
  • 2015
VIEW 8 EXCERPTS
CITES BACKGROUND

FILTER CITATIONS BY YEAR

2013
2019

CITATION STATISTICS

  • 25 Highly Influenced Citations

  • Averaged 25 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 38 REFERENCES

Accelerated

O. Fercoq, P. Richtárik
  • parallel, and proximal coordinate descent, technical report, School of Mathematics, University of Edinburgh
  • 2013
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL