YIHONG WU THESIS

You have access to this content. You have partial access to this content. This paper studies the minimax detection of a small submatrix of elevated mean in a large matrix contaminated by additive Gaussian noise. 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. Permanent link to this document https: Minimax procedures Keywords Asymptotic equivalence high-dimensional statistics computational complexity minimax rate planted clique submatrix detection Citation Ma, Zongming; Wu, Yihong. More like this Computational and statistical boundaries for submatrix localization in a large noisy matrix Cai, T.

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. December First available in Project Euclid: More by Zongming Ma Search this author in: Zentralblatt MATH identifier We provide proofs of Theorem 1 and Lemmas 5 and 6. This paper studies the minimax detection of a small submatrix of elevated mean in a large matrix contaminated by additive Gaussian noise.

More like this Computational and statistical boundaries for submatrix localization in a large noisy matrix Cai, T. Ma, Zongming; Wu, Yihong. You do not have access to this content.

  RCCM PROBLEM SOLVING

Shannon Theory for Compressed Sensing

December First available in Project Euclid: Computational barriers in minimax submatrix detection. Keywords Asymptotic equivalence high-dimensional statistics computational complexity minimax rate planted clique submatrix detection.

Zentralblatt MATH identifier Google Scholar Project Euclid. Abstract Article info and citation First page References Supplemental materials Abstract This paper studies the minimax detection of a thesos submatrix of elevated mean in a large matrix contaminated by additive Gaussian noise.

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.

yihong wu thesis

On combinatorial testing problems. 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: Permanent link to this document https: You have partial access to this content.

We provide proofs of Theorem 1 and Lemmas 5 and 6.

  SHOW M6Y HOMEWORK

Ma , Wu : Computational barriers in minimax submatrix detection

Article information Source Ann. More by Zongming Ma Search this author in: 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.

This paper studies the minimax detection of a small submatrix of elevated thesiss in a large matrix contaminated by additive Gaussian noise. Minimax procedures Keywords Asymptotic equivalence high-dimensional statistics computational complexity minimax rate planted clique submatrix detection Citation Ma, Zongming; Wu, Yihong. Implications on the hardness of support recovery are also obtained.

References [1] Addario-Berry, L. More by Yihong Wu Search this author in: You have access to this content. Computational and statistical boundaries for submatrix localization in a large noisy matrix Cai, T.

yihong wu thesis

MR Digital Object Identifier: