91. Applying random coordinate descent in a probability maximization scheme
Invited abstract in session TD-3: Stochastic optimization and applications I, stream Stochastic optimization and applications.
Thursday, 14:45 - 16:15Room: C 104
Authors (first author is the speaker)
| 1. | Edit Csizmás
|
| Dept. of Informatics, John von Neumann University | |
| 2. | Rajmund Drenyovszki
|
| Dept. of Informatics, John von Neumann University | |
| 3. | Tamas Szantai
|
| Institute of Mathematics, Budapest University of Technology and Economics | |
| 4. | Csaba Fabian
|
| Dept. of Informatics, John von Neumann University |
Abstract
Gradient computation of multivariate distribution functions calls for a considerable effort. A standard procedure is component-wise computation, hence coordinate descent is an attractive choice. This paper deals with constrained convex problems. We apply random coordinate descent in an approximation scheme that is an inexact cutting-plane method from a dual viewpoint. We present convergence proofs and a computational study.
Keywords
- Optimization under uncertainty and applications
- Convex and non-smooth optimization
- Linear and nonlinear optimization
Status: accepted
Back to the list of papers