Details

Autor(en) / Beteiligte

• Butucea, Cristina
• Ndaoud, Mohamed
• Stepanova, Natalia A.
• Tsybakov, Alexandre B.

Titel

VARIABLE SELECTION WITH HAMMING LOSS

Ist Teil von

• The Annals of statistics, 2018-10, Vol.46 (5), p.1837-1875

Ort / Verlag

Hayward: Institute of Mathematical Statistics

Erscheinungsjahr

2018

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• 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.