Screening for a Reweighted Penalized Conditional Gradient Method
The conditional gradient method (CGM) is widely used in large-scale sparse convex optimization, having a low per iteration computational cost for structured sparse regularizers and a greedy approach for collecting nonzeros. We explore the sparsity acquiring properties of a general penalized CGM (P-C...
Saved in:
Main Authors: | Sun, Yifan, Bach, Francis |
---|---|
Format: | Article |
Language: | English |
Published: |
Université de Montpellier
2022-06-01
|
Series: | Open Journal of Mathematical Optimization |
Subjects: | |
Online Access: | https://ojmo.centre-mersenne.org/articles/10.5802/ojmo.14/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
An interior proximal gradient method for nonconvex optimization
by: De Marchi, Alberto, et al.
Published: (2024-07-01) -
The backtrack Hölder gradient method with application to min-max and min-min problems
by: Bolte, Jérôme, et al.
Published: (2023-12-01) -
Short Paper - Quadratic minimization: from conjugate gradient to an adaptive Polyak’s momentum method with Polyak step-sizes
by: Goujaud, Baptiste, et al.
Published: (2024-11-01) -
Convergence Rates of Gradient Methods for Convex Optimization in the Space of Measures
by: Chizat, Lénaïc
Published: (2023-01-01) -
Gradient formulae for probability functions depending on a heterogenous family of constraints
by: van Ackooij, Wim, et al.
Published: (2021-08-01)