VARIABLE SELECTION, MONOTONE LIKELIHOOD RATIO AND

• 成果类型: Article
• 署名作者: Butucea, Cristina; Mammen, Enno; Ndaoud, Mohamed; Tsybakov, Alexandre B.
• 署名单位: Institut Polytechnique de Paris; ENSAE Paris; Ruprecht Karls University Heidelberg; ESSEC Business School
• 刊物名称: ANNALS OF STATISTICS
• ISSN/ISSBN: 0090-5364
• DOI: 10.1214/22-AOS2251
• 发表日期: 2023
• 页码: 312-333
• 关键词: Sufficient conditions; support recovery; SPARSE; PURSUIT; Lasso

摘要

In the pivotal variable selection problem, we derive the exact nonasymptotic minimax selector over the class of all s-sparse vectors, which is also the Bayes selector with respect to the uniform prior. While this optimal selector is, in general, not realizable in polynomial time, we show that its tractable counterpart (the scan selector) attains the minimax expected Hamming risk to within factor 2, and is also exact minimax with respect to the probability of wrong recovery. As a consequence, we establish explicit lower bounds under the monotone likelihood ratio property and we obtain a tight characterization of the minimax risk in terms of the best separable selector risk. We apply these general results to derive necessary and sufficient conditions of exact and almost full recovery in the location model with light tail distributions and in the problem of group variable selection under Gaussian noise and under more general anisotropic sub-Gaussian noise. Numerical results illustrate our theoretical findings.