2017
DOI: 10.1137/16m106340x
|View full text |Cite
|
Sign up to set email alerts
|

Activity Identification and Local Linear Convergence of Forward--Backward-type Methods

Abstract: In this paper, we consider a class of Forward-Backward (FB) splitting methods that includes several variants (e.g. inertial schemes, FISTA) for minimizing the sum of two proper convex and lower semi-continuous functions, one of which has a Lipschitz continuous gradient, and the other is partly smooth relative to a smooth active manifold M. We propose a unified framework, under which we show that, this class of FB-type algorithms (i) correctly identifies the active manifolds in a finite number of iterations (fi… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

5
138
0

Year Published

2018
2018
2020
2020

Publication Types

Select...
7
2

Relationship

3
6

Authors

Journals

citations
Cited by 82 publications
(143 citation statements)
references
References 47 publications
5
138
0
Order By: Relevance
“…We further give bounds, under the assumptions above and the standard nondegeneracy condition, on the active-set complexity of the proximal gradient method. We are only aware of one previous work giving such bounds, the work of Liang et al who included a bound on the active-set complexity of the proximal gradient method [17,Proposition 3.6]. Unlike this work, their result does not evoke strong-convexity.…”
Section: Motivationmentioning
confidence: 92%
“…We further give bounds, under the assumptions above and the standard nondegeneracy condition, on the active-set complexity of the proximal gradient method. We are only aware of one previous work giving such bounds, the work of Liang et al who included a bound on the active-set complexity of the proximal gradient method [17,Proposition 3.6]. Unlike this work, their result does not evoke strong-convexity.…”
Section: Motivationmentioning
confidence: 92%
“…However, there exist accelerated versions such as FISTA [4], which benefit from a better non-asymptotic rate of convergence (O(1/k 2 )). Finally, it is noteworthy that these proximal methods enjoy a linear asymptotic rate (see for instance [64]), but this regime can be slow to reach.…”
Section: Solving the Blassomentioning
confidence: 99%
“…(iii) Theorem 3.3 only states the existence of K after which the identification of the sequences happens, and no bounds are available. In [36,37], lower bounds of K for the FB and DR splitting methods are provided, and similar lower bounds can be obtained here for the Primal-Dual splitting methods. Since such lower-bounds are only of theoretical interest, we decided to skip the corresponding details here and refer the reader to [36,37].…”
mentioning
confidence: 70%
“…The reason behind this is that in the exact case, under condition (ND), the proximal mapping of the partly smooth function R and that of its restriction to M R x locally agree nearby x (and similarly for J * and v ). This property can be easily violated if approximate proximal mappings are involved, see [36] for an example. (iii) Theorem 3.3 only states the existence of K after which the identification of the sequences happens, and no bounds are available.…”
mentioning
confidence: 99%