Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Cherfaoui, Farah"'
We study the properties of the Frank-Wolfe algorithm to solve the m-EXACT-SPARSE reconstruction problem, where a signal y must be expressed as a sparse linear combination of a predefined set of atoms, called dictionary. We prove that when the signal
Externí odkaz:
http://arxiv.org/abs/1905.10443
Publikováno v:
iTWIST: international Traveling Workshop on Interactions between low-complexity data models and Sensing Techniques, Nov 2018, Marseille, France. https://sites.google.com/view/itwist18
In this paper, we study the properties of the Frank-Wolfe algorithm to solve the \ExactSparse reconstruction problem. We prove that when the dictionary is quasi-incoherent, at each iteration, the Frank-Wolfe algorithm picks up an atom indexed by the
Externí odkaz:
http://arxiv.org/abs/1812.07201
Autor:
Cherfaoui, Farah
Publikováno v:
Informatique [cs]. Aix-Marseille Université, 2022. Français. ⟨NNT : ⟩
The contributions of this thesis are divided into two parts. The first part is dedicated to the acceleration of kernel methods and the second to optimization under sparsity constraints. Kernel methods are widely known and used in machine learning. Ho
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______3430::7e9f39acb789703877d566247b6076f3
https://hal.science/tel-04004296/file/manuscrit_CHERFAOUI_final.pdf
https://hal.science/tel-04004296/file/manuscrit_CHERFAOUI_final.pdf
Publikováno v:
ICASSP
ICASSP, May 2022, Singapour, Singapore
ICASSP, May 2022, Singapour, Singapore
International audience; The Nyström method, known as an efficient technique for approximating Gram matrices, builds upon a small subset of the data called landmarks, whose choice impacts the quality of the approximated Gram matrix. Various sampling
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::32adbc8e6683ebbd71f31ebd08a0840f
https://doi.org/10.1109/icassp43922.2022.9747039
https://doi.org/10.1109/icassp43922.2022.9747039
Maximum mean discrepancy (MMD) is a kernelbased distance measure between probability distributions. It relies on the concept of mean embedding of distributions in a Reproducing Kernel Hilbert Space (RKHS). In this work, we describe a new link between
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______3430::72aa2941f29832b0624d94cd0bb804b3
https://hal.science/hal-03651849
https://hal.science/hal-03651849
Autor:
Giffon, Luc, Lamothe, Charly, Bouscarrat, Léo, Milanesi, Paolo, Cherfaoui, Farah, Koço, Sokol
National audience; In this paper we propose a new method to reduce the size of Breiman's Random Forests. Given a Random Forest and a target size, our algorithm builds a linear combination of trees which minimizes the training error. Selected trees, a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::7ac809bd298da17fbdba6e88d994c2d7
https://hal.science/hal-02534421
https://hal.science/hal-02534421