YIHONG WU THESIS

References [1] Addario-Berry, L. Google Scholar Project Euclid. 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. 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. More like this Computational and statistical boundaries for submatrix localization in a large noisy matrix Cai, T. 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:

MR Digital Object Identifier: You have partial access to this content. December First available in Project Euclid: More by Zongming Ma Search this author in: You have access to this content. Implications on the hardness of support recovery are also obtained. Article information Source Ann.

You do not have access to this content.

This paper studies the minimax detection of a small submatrix of elevated eu in a large matrix contaminated by additive Gaussian noise. On combinatorial testing problems.

  M101P HOMEWORK 5.1

yihong wu thesis

Keywords Asymptotic equivalence high-dimensional statistics computational complexity minimax rate planted clique submatrix detection. 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 thessis phase transition phenomenon is established: References [1] Addario-Berry, L. Ma, Zongming; Wu, Yihong.

yihong wu thesis

More like this Computational and tbesis boundaries for submatrix localization in a large noisy matrix Cai, T.

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

Ma , Wu : Computational barriers in minimax submatrix detection

Implications on the hardness of support recovery are also obtained. More by Yihong Wu Search this author in: Article information Source Ann. You have partial access to this content.

yihong wu thesis

Download Email Please enter a valid email address. 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.

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. Computational and statistical boundaries for submatrix localization in yiohng large noisy matrix Cai, T.

  HOMEWORK STÄD OMDÖME

Abstract Article info and citation First page References Supplemental materials Abstract This paper studies the minimax detection of a small yihhong of elevated mean in a large matrix contaminated by additive Gaussian noise. December First available in Project Euclid: We provide proofs of Theorem 1 and Lemmas 5 and 6.

Publications

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

Permanent link to this document https: Zentralblatt MATH identifier More by Zongming Ma Search this author in: MR Digital Object Identifier:

Author: admin