Stochastic Block Mirror Descent Methods for Nonsmooth and Stochastic Optimization

@article{Dang2015StochasticBM,
  title={Stochastic Block Mirror Descent Methods for Nonsmooth and Stochastic Optimization},
  author={Cong D. Dang and Guanghui Lan},
  journal={SIAM Journal on Optimization},
  year={2015},
  volume={25},
  pages={856-881}
}
In this paper, we present a new stochastic algorithm, namely the stochastic block mirror descent (SBMD) method for solving large-scale nonsmooth and stochastic optimization problems. The basic idea of this algorithm is to incorporate the block-coordinate decomposition and an incremental block averaging scheme into the classic (stochastic) mirror-descent method, in order to significantly reduce the cost per iteration of the latter algorithm. We establish the rate of convergence of the SBMD… CONTINUE READING
Highly Cited
This paper has 44 citations. REVIEW CITATIONS
Related Discussions
This paper has been referenced on Twitter 1 time. VIEW TWEETS

From This Paper

Topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 32 extracted citations

Block stochastic gradient iteration for convex and nonconvex optimization

SIAM Journal on Optimization • 2015
View 6 Excerpts
Highly Influenced

Scalable Kernel Methods via Doubly Stochastic Gradients

Bo Dai, Bo Xie, +4 authors Le Song
NIPS • 2014
View 4 Excerpts
Highly Influenced

References

Publications referenced by this paper.
Showing 1-10 of 45 references

The relaxation method of finding the common point convex sets and its application to the solution of problems in convex programming

L. M. Bregman
USSR Comput. Math. Phys., • 1967
View 5 Excerpts
Highly Influenced

Subgradient methods for huge-scale optimization problems

Math. Program. • 2014
View 12 Excerpts
Highly Influenced

Mini-batch stochastic approximation methods for constrained nonconvex stochastic programming. Manuscript, Department of Industrial and Systems Engineering, University of Florida, Gainesville

S. Ghadimi, G. Lan, H. Zhang
FL 32611, • 2013
View 5 Excerpts
Highly Influenced

Efficiency of Coordinate Descent Methods on Huge-Scale Optimization Problems

SIAM Journal on Optimization • 2012
View 12 Excerpts
Highly Influenced

A Stochastic Approximation Method

Herbert Robbins, Sutton Monro
2007
View 3 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…