YIHONG WU THESIS

Zentralblatt MATH identifier 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. Ma, Zongming; Wu, Yihong. MR Digital Object Identifier: More like this Computational and statistical boundaries for submatrix localization in a large noisy matrix Cai, T. 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.

We provide proofs of Theorem 1 and Lemmas 5 and 6. You have access to this content. You have partial access to this content. Computational barriers in minimax 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 following phase transition phenomenon is established:

Publications

MR Digital Object 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.

  OUTSTANDING THESIS AWARD DLSU

Keywords Asymptotic equivalence yihomg statistics computational complexity minimax rate planted clique submatrix detection. On yjhong testing problems.

Zentralblatt MATH identifier Download Email Please enter a valid email address. You have partial access to this content.

Shannon Theory for Compressed Sensing

We provide proofs of Theorem 1 and Lemmas 5 and 6. Ma, Zongming; Wu, Yihong.

yihong wu thesis

References [1] Addario-Berry, L. Google Scholar Project Euclid.

Article information Source Ann. December First available in Project Euclid: This paper studies the minimax detection of a small submatrix of elevated mean in a large matrix contaminated by additive Gaussian noise.

yihong wu thesis

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: You have access to this content.

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

  SUJET DISSERTATION AGRÉGATION EXTERNE ANGLAIS 2016

More by Zongming Ma Search this author in: You do not have access to this content. More by Yihong Wu Search this author in: 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 yihing order than the square root of the graph size, the following yiohng transition phenomenon is established: 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.

Implications on the hardness of support recovery are also obtained. Computational barriers in minimax submatrix detection.