An efficient algorithm to satisfy l1 and l2 constraints

Abstract : An efficient projection enforcing both normalization and sparsity is proposed in this paper. The algorithm has been compared to state of the art methods (binary search and POCS) and provides valuable runtime improvements. Its application within the algorithm associated to Sparse Generalized Canonical Correlation Analysis (SGCCA) has motivated this work.
Document type :
Conference papers
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01630744
Contributor : Arthur Tenenhaus <>
Submitted on : Wednesday, November 8, 2017 - 10:03:01 AM
Last modification on : Tuesday, July 23, 2019 - 12:42:02 PM
Long-term archiving on : Friday, February 9, 2018 - 12:19:21 PM

File

Gloaguen_et_al_2017.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01630744, version 1

Citation

Arnaud Gloaguen, Vincent Guillemot, Arthur Tenenhaus. An efficient algorithm to satisfy l1 and l2 constraints. 49èmes Journées de Statistique, May 2017, Avignon, France. ⟨hal-01630744⟩

Share

Metrics

Record views

274

Files downloads

120