Conference proceeding
Stochastic Three-Composite Convex Minimization with a Linear Operator
INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 84, Vol.84
Proceedings of Machine Learning Research
01/01/2018
Abstract
We develop a primal-dual convex minimization framework to solve a class of stochastic convex three-composite problem with a linear operator. We consider the cases where the problem is both convex and strongly convex and analyze the convergence of the proposed algorithm in both cases. In addition, we extend the proposed framework to deal with additional constraint sets and multiple non-smooth terms. We provide numerical evidence on graph-guided sparse logistic regression, fused lasso and overlapped group lasso, to demonstrate the superiority of our approach to the state-of-the-art.
Details
- Title: Subtitle
- Stochastic Three-Composite Convex Minimization with a Linear Operator
- Creators
- Renbo Zhao - Federal ReserveVolkan Cevher - Federal Reserve
- Contributors
- A Storkey (Editor)F PerezCruz (Editor)
- Resource Type
- Conference proceeding
- Publication Details
- INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 84, Vol.84
- Publisher
- Microtome Publishing
- Series
- Proceedings of Machine Learning Research
- ISSN
- 2640-3498
- Number of pages
- 10
- Grant note
- 725594 / European Research Council under the European Union's Horizon 2020 research and innovation program
- Language
- English
- Date published
- 01/01/2018
- Academic Unit
- Business Analytics
- Record Identifier
- 9984446415902771
Metrics
1 Record Views