Show simple item record

hal.structure.identifierModélisation aléatoire de Paris X [MODAL'X]
dc.contributor.authorCollier, Olivier
hal.structure.identifierCEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
dc.contributor.authorComminges, Laëtitia
HAL ID: 11573
hal.structure.identifierEcole Nationale de la Statistique et de l'Analyse Economique [ENSAE]
dc.contributor.authorTsybakov, Alexandre
dc.subjectlinear functionalen
dc.subjectNonasymptotic minimax estimationen
dc.subjectquadratic functionalen
dc.subjectunknown noise varianceen
dc.titleMinimax estimation of linear and quadratic functionals on sparsity classesen
dc.typeArticle accepté pour publication ou publié
dc.description.abstractenFor the Gaussian sequence model, we obtain nonasymptotic minimax rates of estimation of the linear, quadratic and the ℓ2-norm functionals on classes of sparse vectors and construct optimal estimators that attain these rates. The main object of interest is the class B0(s) of s-sparse vectors θ=(θ1,…,θd), for which we also provide completely adaptive estimators (independent of s and of the noise variance σ) having logarithmically slower rates than the minimax ones. Furthermore, we obtain the minimax rates on the ℓq-balls Bq(r)={θ∈Rd:∥θ∥q≤r} where 0<q≤2, and ∥θ∥q=(∑di=1|θi|q)1/q. This analysis shows that there are, in general, three zones in the rates of convergence that we call the sparse zone, the dense zone and the degenerate zone, while a fourth zone appears for estimation of the quadratic functional. We show that, as opposed to estimation of θ, the correct logarithmic terms in the optimal rates for the sparse zone scale as log(d/s2) and not as log(d/s). For the class B0(s), the rates of estimation of the linear functional and of the ℓ2-norm have a simple elbow at s=√d (boundary between the sparse and the dense zones) and exhibit similar performances, whereas the estimation of the quadratic functional Q(θ) reveals more complex effects: the minimax risk on B0(s) is infinite and the sparseness assumption needs to be combined with a bound on the ℓ2-norm. Finally, we apply our results on estimation of the ℓ2-norm to the problem of testing against sparse alternatives. In particular, we obtain a nonasymptotic analog of the Ingster–Donoho–Jin theory revealing some effects that were not captured by the previous asymptotic analysis.en
dc.relation.isversionofjnlnameAnnals of Statistics
dc.relation.isversionofjnlpublisherInstitute of Mathematical Statisticsen
dc.subject.ddclabelProbabilités et mathématiques appliquéesen

Files in this item


There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record