Loading...
Please wait, while we are loading the content...
Similar Documents
Adaptive Stochastic Primal-Dual Coordinate Descent for Separable Saddle Point Problems
| Content Provider | Semantic Scholar |
|---|---|
| Author | Appice, Annalisa Rodrigues, P. Costa, Vítor Santos Soares, C. Gama, João Jorge, A. |
| Copyright Year | 2015 |
| Abstract | We consider a generic convex-concave saddle point problem with a separable structure, a form that covers a wide-ranged machine learning applications. Under this problem structure, we follow the framework of primal-dual updates for saddle point problems, and incorporate stochastic block coordinate descent with adaptive stepsizes into this framework. We theoretically show that our proposal of adaptive stepsizes potentially achieves a sharper linear convergence rate compared with the existing methods. Additionally, since we can select “mini-batch” of block coordinates to update, our method is also amenable to parallel processing for large-scale data. We apply the proposed method to regularized empirical risk minimization and show that it performs comparably or, more often, better than state-of-the-art methods on both synthetic and real-world data sets. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | https://www.research.ed.ac.uk/portal/files/22076376/Storkey_2015_Adaptive_Stochastic_Primal_Dual_Coordinate.pdf |
| Alternate Webpage(s) | http://www.research.ed.ac.uk/portal/files/22076376/Storkey_2015_Adaptive_Stochastic_Primal_Dual_Coordinate.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
