YIHONG WU THESIS

YIHONG WU THESIS

Google Scholar Project Euclid. Article information Source Ann. 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. This paper studies the minimax detection of a small submatrix of elevated mean in a large matrix contaminated by additive Gaussian noise. You do not have access to this content. You have access to this content. More like this Computational and statistical boundaries for submatrix localization in a large noisy matrix Cai, T.

MR Digital Object Identifier: Google Scholar Project Euclid. This paper studies the minimax detection of a small submatrix of elevated mean in a large matrix contaminated by additive Gaussian noise. 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: You do not 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.

  GRIMSBY EAGLES HOMEWORK PAGE

yihong wu thesis

December First available in Project Euclid: Zentralblatt MATH identifier Abstract Article ylhong 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.

More by Zongming Ma Search this author in: Permanent du to this document https: Download Email Please enter a valid email address. Ma, Zongming; Wu, Yihong. References [1] Addario-Berry, L.

Shannon Theory for Compressed Sensing

On combinatorial testing problems. 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. 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, uihong following phase transition phenomenon is established: We provide proofs of Theorem 1 and Lemmas 5 and 6.

Publications

Computational barriers in minimax submatrix detection. More by Yihong Wu Search this author in: Computational and statistical boundaries for submatrix localization in a large noisy matrix Cai, T. You have access to this content. Implications on the hardness of support recovery are also obtained.

  MATHS PROBLEM SOLVING KS1 NRICH

yihong wu thesis

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. Tesis Asymptotic equivalence high-dimensional statistics computational complexity minimax rate planted clique submatrix detection.

MR Digital Object Identifier: Article information Source Ann.

Google Scholar Project Euclid. You have partial access to this content.

You do not have access to this content. To investigate the tradeoff between statistical performance and tthesis cost from a complexity-theoretic perspective, we consider a sequence of discretized models which are asymptotically equivalent to the Gaussian model.