We derive nonasymptotic bounds for the minimax risk of variable selection under expected Hamming loss in the Gaussian mean model in Rd 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.

, , , , , ,
doi.org/10.1214/17-AOS1572
Annals of Statistics
School of Mathematics and Statistics

Butucea, C. (Cristina), Ndaoud, M. (Mohamed), Stepanova, N, & Tsybakov, A.B. (Alexandre B.). (2018). Variable selection with hamming loss. Annals of Statistics, 46(5), 1837–1875. doi:10.1214/17-AOS1572