2017
DOI: 10.1214/15-aos1432
|View full text |Cite
|
Sign up to set email alerts
|

Minimax estimation of linear and quadratic functionals on sparsity classes

Abstract: For the Gaussian sequence model, we obtain non-asymp-totic minimax rates of estimation of the linear, quadratic and the ℓ 2 -norm functionals on classes of sparse vectors and construct optimal estimators that attain these rates. The main object of interest is the class B 0 (s) of s-sparse vectors θ = (θ 1 , . . . , θ d ), for which we also provide completely adaptive estimators (independent of s and of the noise variance σ) having only logarithmically slower rates than the minimax ones. Furthermore, we obtain … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

5
92
0

Year Published

2018
2018
2023
2023

Publication Types

Select...
8
1

Relationship

2
7

Authors

Journals

citations
Cited by 65 publications
(97 citation statements)
references
References 36 publications
5
92
0
Order By: Relevance
“…Note that the rate λ defined in this way is a non-asymptotic minimax rate of testing as opposed to the classical asymptotic definition that can be found, for example, in Ingster and Suslina (2003). It is shown in Collier, Comminges and Tsybakov (2017) that when X is the identity matrix and p = n (which corresponds to the Gaussian sequence model), the non-asymptotic minimax rate of testing on the class B 0 (s) with respect to the ℓ 2 -distance has the following form:…”
Section: Introductionmentioning
confidence: 99%
“…Note that the rate λ defined in this way is a non-asymptotic minimax rate of testing as opposed to the classical asymptotic definition that can be found, for example, in Ingster and Suslina (2003). It is shown in Collier, Comminges and Tsybakov (2017) that when X is the identity matrix and p = n (which corresponds to the Gaussian sequence model), the non-asymptotic minimax rate of testing on the class B 0 (s) with respect to the ℓ 2 -distance has the following form:…”
Section: Introductionmentioning
confidence: 99%
“…The signal detection problem which amounts to testing whether θ = 0 is a special instance of the sparsity testing problem (corresponding to k 0 = 0). Signal detection in the Gaussian vector model has been extensively studied [3,14,17,25] in the last fifteen years and is now well understood. For instance, it has been established in [14] that the minimax separation distance ρ * γ [0, ∆] satisfies…”
Section: Related Literaturementioning
confidence: 99%
“…This entails that it is possible to detect sparse vectors θ whose non-zero values are of order log(n/∆ 2 ). Known optimal tests such as the higher criticism test [17] or the one proposed in [14] amount to counting the number of values |Y i | that are larger than t and to compare this number to what is expected under the null hypothesis. Doing this simultaneously for a wide range of t leads to near-optimal performances simultaneously for all ∆ ∈ [1, √ n].…”
Section: Related Literaturementioning
confidence: 99%
“…-Finally, considering inverse problems with sparsity constraints as in [CCT17] might be of interest.…”
Section: Conclusion and Open Questionsmentioning
confidence: 99%