|
|
|
|
| LEADER |
01361 am a22002173u 4500 |
| 001 |
117359 |
| 042 |
|
|
|a dc
|
| 100 |
1 |
0 |
|a Lin, Junhong
|e author
|
| 100 |
1 |
0 |
|a Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
|e contributor
|
| 100 |
1 |
0 |
|a Rosasco, Lorenzo
|e contributor
|
| 700 |
1 |
0 |
|a Rosasco, Lorenzo
|e author
|
| 700 |
1 |
0 |
|a Villa, Silvia
|e author
|
| 700 |
1 |
0 |
|a Zhou, Ding-Xuan
|e author
|
| 245 |
0 |
0 |
|a Modified Fejér sequences and applications
|
| 260 |
|
|
|b Springer US,
|c 2018-08-14T17:52:33Z.
|
| 856 |
|
|
|z Get fulltext
|u http://hdl.handle.net/1721.1/117359
|
| 520 |
|
|
|a In this note, we propose and study the notion of modified Fejér sequences. Within a Hilbert space setting, this property has been used to prove ergodic convergence of proximal incremental subgradient methods. Here we show that indeed it provides a unifying framework to prove convergence rates for objective function values of several optimization algorithms. In particular, our results apply to forward-backward splitting algorithm, incremental subgradient proximal algorithm, and the Douglas-Rachford splitting method including and generalizing known results.
|
| 520 |
|
|
|a Italy. Ministry of Education, University, Scientific and Technological Research (FIRB Project RBFR12M3AC)
|
| 546 |
|
|
|a en
|
| 655 |
7 |
|
|a Article
|
| 773 |
|
|
|t Computational Optimization and Applications
|
