Primal-dual subgradient method for convex problems with functional constraints
Event details
| Date | 14.11.2014 |
| Hour | 11:15 › 12:00 |
| Speaker | Yurii Nesterov, Ecole Polytechnique de Louvain |
| Location | |
| Category | Conferences - Seminars |
Abstract
In this talk we present a new primal-dual method for solving nonsmooth constrained optimization problem with functional constraints. This method consists in parallel updates of primal and dual variables, such that the dual updates can be seen as a coordinate descent scheme. Nevertheless, it has best possible performance guarantees. We show that such a method can be applied to sparse problems of very big size, ensuring the logarithmic dependence of iteration complexity in the problem’s dimension.
Biography
Yurii Nesterov is a professor at Center for Operations Research and Econometrics (CORE) in the Catholic University of Louvain (UCL), Belgium. He received his Ph.D. degree (Applied Mathematics) in 1984 at the Institute of Control Sciences, Moscow. His research interests are related to complexity issues and efficient methods for solving various optimization problems. His main research interestes are in Convex Optimization (optimal methods for smooth problems, polynomial-time interior-point methods, smoothing technique for structural optimization, cubic regularization of Newton method, optimization methods for huge-scale problems).
In this talk we present a new primal-dual method for solving nonsmooth constrained optimization problem with functional constraints. This method consists in parallel updates of primal and dual variables, such that the dual updates can be seen as a coordinate descent scheme. Nevertheless, it has best possible performance guarantees. We show that such a method can be applied to sparse problems of very big size, ensuring the logarithmic dependence of iteration complexity in the problem’s dimension.
Biography
Yurii Nesterov is a professor at Center for Operations Research and Econometrics (CORE) in the Catholic University of Louvain (UCL), Belgium. He received his Ph.D. degree (Applied Mathematics) in 1984 at the Institute of Control Sciences, Moscow. His research interests are related to complexity issues and efficient methods for solving various optimization problems. His main research interestes are in Convex Optimization (optimal methods for smooth problems, polynomial-time interior-point methods, smoothing technique for structural optimization, cubic regularization of Newton method, optimization methods for huge-scale problems).
Practical information
- Expert
- Free