2023
DOI: 10.1016/j.ejor.2022.09.030
|View full text |Cite
|
Sign up to set email alerts
|

A decomposition method for lasso problems with zero-sum constraint

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
2
1
1

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(2 citation statements)
references
References 41 publications
0
2
0
Order By: Relevance
“…We focused on methylation patterns at CpG sites for our study, since this is the major methylation context in vertebrates (Klughammer et al 2023). To improve coverage and minimise pseudo-replication, we further de-stranded adjacent cytosines per CpG site using the ‘merge_CpG.py’ script (Cristofari, 2023), as methylation occurs symmetrically at CpG sites in vertebrates (Klughammer et al 2023). On average, this resulted in 24,947,580 ± 825,959 (SD) CpG sites per sample, with a de-stranded coverage of 8.56 ± 0.93 (SD) X ( Table S1 ).…”
Section: Methodsmentioning
confidence: 99%
“…We focused on methylation patterns at CpG sites for our study, since this is the major methylation context in vertebrates (Klughammer et al 2023). To improve coverage and minimise pseudo-replication, we further de-stranded adjacent cytosines per CpG site using the ‘merge_CpG.py’ script (Cristofari, 2023), as methylation occurs symmetrically at CpG sites in vertebrates (Klughammer et al 2023). On average, this resulted in 24,947,580 ± 825,959 (SD) CpG sites per sample, with a de-stranded coverage of 8.56 ± 0.93 (SD) X ( Table S1 ).…”
Section: Methodsmentioning
confidence: 99%
“…In the unconstrained case we can choose as working set, for instance, the block corresponding to the largest component of the gradient in absolute value. Also for this rule, exact or inexact minimizations can be carried out to update the variables [14,17,25,37] and extensions to constrained settings were considered in the literature [3,35,44,55,56]. Generally speaking, a greedy rule might make more progress in the objective function, since it uses first (or higher) order information to choose the working set, but might be, in principle, more expensive than cyclic or random selection.…”
Section: Block Coordinate Descent Approachesmentioning
confidence: 99%