Minimax Estimation of Linear and Quadratic Functionals on Sparsity Classes

Olivier Collier (), Laëtitia Comminges () and Alexandre Tsybakov ()
Additional contact information
Olivier Collier: Modal’X, Université Paris-Ouest
Laëtitia Comminges: Université Paris Dauphine
Alexandre Tsybakov: CREST, ENSAE

No 2016-09, Working Papers from Center for Research in Economics and Statistics

Abstract: For the Gaussian sequence model, we obtain non-asymptotic 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 ? = (?1, …, ?d), for which we also provide completely adaptive estimators (independent of s and of the noise variance having logarithmically slower rates than the minimax ones. 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 ?, 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=vd (boundary between the sparse and the dense zones) and exhibit similar performances, whereas the estimation of the quadratic functional Q(?) 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 non-asymptotic analog of the Ingster-Donoho-Jin theory revealing some effects that were not captured by the previous asymptotic analysis.

Keywords: nonasymptotic minimax estimation; linear functional; quadratic functional; sparsity; unknown noise variance; thresholding (search for similar items in EconPapers)
Pages: 31
Date: 2016-01
References: Add references at CitEc
Citations:

Downloads: (external link)
http://crest.science/RePEc/wpstorage/2016-09.pdf Crest working paper version (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:crs:wpaper:2016-09

Access Statistics for this paper

More papers in Working Papers from Center for Research in Economics and Statistics Contact information at EDIRC.
Bibliographic data for series maintained by Secretariat General () and Murielle Jules Maintainer-Email : murielle.jules@ensae.Fr.