A phase transition for finding needles in nonlinear haystacks with LASSO artificial neural networks

To fit sparse linear associations, a LASSO sparsity inducing penalty with a single hyperparameter provably allows to recover the important features (needles) with high probability in certain regimes even if the sample size is smaller than the dimension of the input vector (haystack). More recently l...

Descripción completa

Detalles Bibliográficos
Autores principales: Ma, Xiaoyu, Sardy, Sylvain, Hengartner, Nick, Bobenko, Nikolai, Lin, Yen Ting
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer US 2022
Materias:
OriginalPaper
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9587964/
https://www.ncbi.nlm.nih.gov/pubmed/36299529
http://dx.doi.org/10.1007/s11222-022-10169-0

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9587964/
https://www.ncbi.nlm.nih.gov/pubmed/36299529
http://dx.doi.org/10.1007/s11222-022-10169-0

Ejemplares similares