Corpus ID: 13451663

Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization

@inproceedings{Zhang2015StochasticPC,
  title={Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization},
  author={Yuchen Zhang and Xiao Lin},
  booktitle={ICML},
  year={2015}
}
We consider a generic convex optimization problem associated with regularized empirical risk minimization of linear predictors. The problem structure allows us to reformulate it as a convex-concave saddle point problem. We propose a stochastic primal-dual coordinate method, which alternates between maximizing over one (or more) randomly chosen dual variable and minimizing over the primal variable. We also develop an extension to non-smooth and nonstrongly convex loss functions, and an extension… Expand
On Stochastic Primal-Dual Hybrid Gradient Approach for Compositely Regularized Minimization
Doubly Stochastic Primal-Dual Coordinate Method for Bilinear Saddle-Point Problem
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 79 REFERENCES
Dual Averaging Methods for Regularized Stochastic Learning and Online Optimization
  • Lin Xiao
  • Computer Science, Mathematics
  • J. Mach. Learn. Res.
  • 2009
A Proximal Stochastic Gradient Method with Progressive Variance Reduction
Randomized Dual Coordinate Ascent with Arbitrary Sampling
...
1
2
3
4
5
...