Accelerated Coordinate Descent with Arbitrary Sampling and Best Rates for Minibatches

@inproceedings{Hanzely2018AcceleratedCD,
  title={Accelerated Coordinate Descent with Arbitrary Sampling and Best Rates for Minibatches},
  author={Filip Hanzely and Peter Richt{\'a}rik},
  booktitle={AISTATS},
  year={2018}
}
Accelerated coordinate descent is a widely popular optimization algorithm due to its efficiency on large-dimensional problems. It achieves state-of-the-art complexity on an important class of empirical risk minimization problems. In this paper we design and analyze an accelerated coordinate descent (\texttt{ACD}) method which in each iteration updates a random subset of coordinates according to an arbitrary but fixed probability law, which is a parameter of the method. While mini-batch… CONTINUE READING
1
Twitter Mention

References

Publications referenced by this paper.
SHOWING 1-10 OF 36 REFERENCES

Accelerated, Parallel and Proximal Coordinate Descent

  • SIAM Journal on Optimization
  • 2013
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Efficiency of Coordinate Descent Methods on Huge-Scale Optimization Problems

  • SIAM Journal on Optimization
  • 2012
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Coordinate descent with arbitrary sampling I: algorithms and complexity

  • Optimization Methods and Software
  • 2014
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Coordinate descent with arbitrary sampling II: expected separable overapproximation

  • Optimization Methods and Software
  • 2014
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Fast distributed coordinate descent for non-strongly convex losses

  • 2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)
  • 2014
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers