Name
Abstract | ||
|---|---|---|
This paper introduces AdaSDCA: an adaptive variant of stochastic dual coordinate ascent (SDCA) for solving the regularized empirical risk minimization problems. Our modification consists in allowing the method to adaptively change the probability distribution over the dual variables throughout the iterative process. AdaSDCA achieves provably better complexity bound than SDCA with the best fixed probability distribution, known as importance sampling. However, it is of a theoretical character as it is expensive to implement. We also propose AdaSDCA+: a practical variant which in our experiments outperforms existing non-adaptive methods. |
Year | Venue | Field |
|---|---|---|
2015 | International Conference on Machine Learning | Importance sampling,Mathematical optimization,Iterative and incremental development,Computer science,Empirical risk minimization,Algorithm,Probability distribution |
DocType | Volume | Citations |
Journal | abs/1502.08053 | 24 |
PageRank | References | Authors |
0.86 | 32 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| dominik csiba | 1 | 55 | 2.80 |
| Zheng Qu | 2 | 151 | 27.47 |
| Peter Richtárik | 3 | 52 | 5.66 |