Conference proceeding
An Optimal Algorithm for Stochastic Three-Composite Optimization
22ND INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 89, Vol.89, pp.428-437
Proceedings of Machine Learning Research
01/01/2019
Abstract
We develop an optimal primal-dual first order algorithm for a class of stochastic three-composite convex minimization problems. The convergence rate of our method not only improves upon the existing methods, but also matches a lower bound derived for all first-order methods that solve this problem. We extend our proposed algorithm to solve a composite stochastic program with any finite number of nonsmooth functions. In addition, we generalize an optimal stochastic alternating direction method of multipliers (SADMM) algorithm proposed for the two-composite case to solve this problem, and establish its connection to our optimal primal-dual algorithm. We perform extensive numerical experiments on a variety of machine learning applications to demonstrate the superiority of our method via-a-vis the state-of-the-art.
Details
- Title: Subtitle
- An Optimal Algorithm for Stochastic Three-Composite Optimization
- Creators
- Renbo Zhao - MIT, ORC, 77 Massachusetts Ave, Cambridge, MA 02139 USAWilliam B. Haskell - University Hospital of UmeåVincent Y. F. Tan - University Hospital of Umeå
- Contributors
- K Chaudhuri (Editor)M Sugiyama (Editor)
- Resource Type
- Conference proceeding
- Publication Details
- 22ND INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 89, Vol.89, pp.428-437
- Publisher
- Microtome Publishing
- Series
- Proceedings of Machine Learning Research
- ISSN
- 2640-3498
- Number of pages
- 10
- Language
- English
- Date published
- 01/01/2019
- Academic Unit
- Business Analytics
- Record Identifier
- 9984446441002771
Metrics
3 Record Views