A Fixed-Point of View on Gradient Methods for Big Data
Interpreting gradient methods as fixed-point iterations, we provide a detailed analysis of those methods for minimizing convex objective functions. Due to their conceptual and algorithmic simplicity, gradient methods are widely used in machine learning for massive data sets (big data). In particular...
| Published in: | Frontiers in Applied Mathematics and Statistics |
|---|---|
| Main Author: | |
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2017-09-01
|
| Subjects: | |
| Online Access: | http://journal.frontiersin.org/article/10.3389/fams.2017.00018/full |