کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
1145225 | 1489654 | 2016 | 13 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Worst possible sub-directions in high-dimensional models
ترجمه فارسی عنوان
بدترین جابه جایی های زیر در مدل های با ابعاد بزرگ
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
موضوعات مرتبط
مهندسی و علوم پایه
ریاضیات
آنالیز عددی
چکیده انگلیسی
We examine the rate of convergence of the Lasso estimator of lower dimensional components of the high-dimensional parameter. Under bounds on the â1-norm on the worst possible sub-direction these rates are of order |J|logp/n where p is the total number of parameters, n is the number of observations and Jâ{1,â¦,p} represents a subset of the parameters. We also derive rates in sup-norm in terms of the rate of convergence in â1-norm. The irrepresentable condition on a set J requires that the â1-norm of the worst possible sub-direction is sufficiently smaller than one. In that case sharp oracle results can be obtained. Moreover, if the coefficients in J are small enough the Lasso will put these coefficients to zero. By de-sparsifying one obtains fast rates in supremum norm without conditions on the worst possible sub-direction. The results are extended to M-estimation with â1-penalty for generalized linear models and exponential families. For the graphical Lasso this leads to an extension of known results to the case where the precision matrix is only approximately sparse. The bounds we provide are non-asymptotic but we also present asymptotic formulations for ease of interpretation.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Journal of Multivariate Analysis - Volume 146, April 2016, Pages 248-260
Journal: Journal of Multivariate Analysis - Volume 146, April 2016, Pages 248-260
نویسندگان
Sara van de Geer,