Stochastic First-Order Methods with Random Constraint Projection
We consider convex optimization problems with structures that are suitable for sequential treatment or online sampling. In particular, we focus on problems where the objective function is an expected value, and the constraint set is the intersection of a large number of simpler sets. We propose an a...
Main Authors: | Wang, Mengdi (Author), Bertsekas, Dimitri P. (Contributor) |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor), Massachusetts Institute of Technology. Laboratory for Information and Decision Systems (Contributor) |
Format: | Article |
Language: | English |
Published: |
Society for Industrial and Applied Mathematics (SIAM),
2016-07-20T16:52:35Z.
|
Subjects: | |
Online Access: | Get fulltext |
Similar Items
-
Incremental constraint projection methods for variational inequalities
by: Wang, Mengdi, et al.
Published: (2015) -
Stabilization of Stochastic Iterative Methods for Singular and Nearly Singular Linear Systems
by: Wang, Mengdi, et al.
Published: (2015) -
On Boundedness of Q-Learning Iterates for Stochastic Shortest Path Problems
by: Yu, Huizhen, et al.
Published: (2015) -
Q-learning and policy iteration algorithms for stochastic shortest path problems
by: Yu, Huizhen, et al.
Published: (2015) -
A unified framework for temporal difference methods
by: Bertsekas, Dimitri P.
Published: (2010)