VARIABLE SELECTION WITH HAMMING LOSS

Cristina Butucea

doi:10.1214/17-AOS1572

VARIABLE SELECTION WITH HAMMING LOSS

2018-10-01

30

OA

AI

Alexandre B. Tsybakov

DOI：10.1214/17-AOS1572

原文链接

查看原文

摘要

En 中文

We derive nonasymptotic bounds for the minimax risk of variable selection under expected Hamming loss in the Gaussian mean model in R-d for classes of at most s-sparse vectors separated from 0 by a constant a > 0. In some cases, we get exact expressions for the nonasymptotic minimax risk as a function of d, s, a and find explicitly the minimax selectors. These results are extended to dependent or non-Gaussian observations and to the problem of crowdsourcing. Analogous conclusions are obtained for the probability of wrong recovery of the sparsity pattern. As corollaries, we derive necessary and sufficient conditions for such asymptotic properties as almost full recovery and exact recovery. Moreover, we propose data-driven selectors that provide almost full and exact recovery adaptively to the parameters of the classes.

Keyword:

Adaptive variable selection

almost full recovery

exact recovery

Hamming loss

minimax selectors

nonasymptotic minimax selection bounds

phase transitions

VARIABLE SELECTION WITH HAMMING LOSS

摘要

AI总结

期刊

机构