Lataa...

OPTIMAL COMPUTATIONAL AND STATISTICAL RATES OF CONVERGENCE FOR SPARSE NONCONVEX LEARNING PROBLEMS

We provide theoretical analysis of the statistical and computational properties of penalized M-estimators that can be formulated as the solution to a possibly nonconvex optimization problem. Many important estimators fall in this category, including least squares regression with nonconvex regulariza...

Täydet tiedot

Tallennettuna:
Bibliografiset tiedot
Julkaisussa:Ann Stat
Päätekijät: Wang, Zhaoran, Liu, Han, Zhang, Tong
Aineistotyyppi: Artigo
Kieli:Inglês
Julkaistu: 2014
Aiheet:
Linkit:https://ncbi.nlm.nih.gov/pmc/articles/PMC4276088/
https://ncbi.nlm.nih.gov/pubmed/25544785
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1214/14-AOS1238
Tagit: Lisää tagi
Ei tageja, Lisää ensimmäinen tagi!