YIHONG WU THESIS

YIHONG WU THESIS

You do not have access to this content. On combinatorial testing problems. Zentralblatt MATH identifier Abstract Article info and citation First page References Supplemental materials Abstract This paper studies the minimax detection of a small submatrix of elevated mean in a large matrix contaminated by additive Gaussian noise. Ma, Zongming; Wu, Yihong.

Google Scholar Project Euclid. Zentralblatt MATH identifier You have access to this content. Download Email Please enter a valid email address. You do not have access to this content.

Permanent link to this document https: We provide proofs of Theorem 1 and Lemmas 5 and 6. More like this Computational and statistical boundaries for submatrix localization in a large noisy matrix Cai, T.

Ma , Wu : Computational barriers in minimax submatrix detection

More by Zongming Ma Search this author in: This paper studies the minimax detection of a small submatrix of elevated mean in a large matrix contaminated by additive Gaussian noise. On combinatorial testing problems. You have access to this content. December First available in Project Euclid: Article information Thessis Ann.

  COVER LETTER SCRIPTA MATERIALIA

Yihong Wu :: ECE ILLINOIS

MR Digital Object Identifier: More by Yihong Wu Search this author in: Ma, Zongming; Wu, Yihong. Keywords Asymptotic equivalence high-dimensional statistics computational complexity minimax rate planted clique submatrix detection.

Minimax procedures Keywords Asymptotic equivalence high-dimensional statistics computational complexity minimax rate planted clique submatrix detection Citation Ma, Zongming; Wu, Yihong.

yihong wu thesis

To investigate the tradeoff between statistical performance and computational cost from a complexity-theoretic perspective, we consider a sequence of discretized models which are asymptotically equivalent to the Gaussian model.

You have partial access to this content.

Publications

Download Email Please enter theais valid email address. Abstract Article info and citation First page References Supplemental materials Abstract This paper studies the minimax detection of a small submatrix of elevated mean in a large matrix contaminated by additive Gaussian noise. Using Schatten norm loss as a representative example, we show that the hardness of attaining the minimax estimation rate can crucially depend on the loss function.

  TMCC CREATIVE WRITING

You do not have access to this content. yihonh

yihong wu thesis

Computational and statistical boundaries for submatrix localization in du large noisy matrix Cai, T. Zentralblatt MATH identifier Under the hypothesis that the planted clique detection problem cannot be solved in randomized polynomial time when the clique size is of smaller order than the square root of the graph size, the following phase transition phenomenon is established: References [1] Addario-Berry, L.

Google Scholar Project Euclid. Computational barriers in minimax submatrix detection.

Implications on the hardness of support recovery are also obtained.