publication . Preprint . 2017

On Estimation of $L_{r}$-Norms in Gaussian White Noise Models

Han, Yanjun; Jiao, Jiantao; Mukherjee, Rajarshi;
Open Access English
  • Published: 10 Oct 2017
We provide a complete picture of asymptotically minimax estimation of $L_r$-norms (for any $r\ge 1$) of the mean in Gaussian white noise model over Nikolskii-Besov spaces. In this regard, we complement the work of Lepski, Nemirovski and Spokoiny (1999), who considered the cases of $r=1$ (with poly-logarithmic gap between upper and lower bounds) and $r$ even (with asymptotically sharp upper and lower bounds) over H\"{o}lder spaces. We additionally consider the case of asymptotically adaptive minimax estimation and demonstrate a difference between even and non-even $r$ in terms of an investigator's ability to produce asymptotically adaptive minimax estimators with...
arXiv: Statistics::Theory
free text keywords: Mathematics - Statistics Theory, Computer Science - Machine Learning
Funded by
NSF| Emerging Frontiers of Science of Information
  • Funder: National Science Foundation (NSF)
  • Project Code: 0939370
  • Funding stream: Directorate for Computer & Information Science & Engineering | Division of Computing and Communication Foundations
Download from
47 references, page 1 of 4

Lemma 5.2. Under the conditions of Theorem 3.4, the following hold for all x ∈ [0, 1], k ≥ 2, c1 > √8k, and constants C1 (depending on (c1, c2, ǫ, σ, KM )) and C2 (depending on (c1, c2, ǫ, σ, KM , k)).

= P Lemma 6.3. (Boucheron, Lugosi and Massart, 2013) For X ∼ N (µ, σ 2), we have Lemma 6.12. Let X, Y ∼ N (µ, λ 2h) be independent, k ≥ 2 be any integer, 4c21 ≥ c2, c2 ln n ≥ 1, and c1 > √8k, 7c2 ln 2 < ǫ ∈ (0, 1), nh ≥ 1. Then there exists constants C1 (depending on (c1, c2, ǫ, KM )) and C2 (depending on (c1, c2, ǫ, KM , k)) such that the following hold.

Birg´e, L. and Massart, P. (1995). Estimation of integral functionals of a density. The Annals of Statistics 11-29. [OpenAIRE]

Boucheron, S., Lugosi, G. and Massart, P. (2013). Concentration inequalities: A nonasymptotic theory of independence. Oxford University Press.

Cai, T. T. and Low, M. G. (2003). A note on nonparametric estimation of linear functionals. Annals of statistics 1140-1153.

Cai, T. T. and Low, M. G. (2004). Minimax estimation of linear functionals over nonconvex parameter spaces. Annals of statistics 552-576. [OpenAIRE]

Cai, T. T. and Low, M. G. (2005). Nonquadratic estimators of a quadratic functional. The Annals of Statistics 2930-2956. [OpenAIRE]

Cai, T. T. and Low, M. G. (2011). Testing composite hypotheses, Hermite polynomials and optimal estimation of a nonsmooth functional. The Annals of Statistics 39 1012-1041. [OpenAIRE]

Carpentier, A. (2013). Honest and adaptive confidence sets in L {p}. Electronic Journal of Statistics 7 2875-2923.

DeVore, R. A. and Lorentz, G. G. (1993). Constructive approximation 303. Springer.

Ditzian, Z. and Totik, V. (1987). Moduli of smoothness. Springer.

Donoho, D. L., Liu, R. C. and MacGibbon, B. (1990). Minimax risk over hyperrectangles, and implications. The Annals of Statistics 1416-1437. [OpenAIRE]

Donoho, D. L. and Nussbaum, M. (1990). Minimax quadratic estimation of a quadratic functional. Journal of Complexity 6 290-323. [OpenAIRE]

Fan, J. (1991). On the estimation of quadratic functionals. The Annals of Statistics 1273-1294.

Gin´e, E. and Nickl, R. (2015). Mathematical foundations of infinite-dimensional statistical models 40. Cambridge University Press. [OpenAIRE]

47 references, page 1 of 4
Powered by OpenAIRE Open Research Graph
Any information missing or wrong?Report an Issue