YIHONG WU THESIS

  • July 8, 2019

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. This paper studies the minimax detection of a small submatrix of elevated mean in a large matrix contaminated by additive Gaussian noise. Computational and statistical boundaries for submatrix localization in a large noisy matrix Cai, T. References [1] Addario-Berry, L. 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. We provide proofs of Theorem 1 and Lemmas 5 and 6.

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. You have partial access to this content. On combinatorial testing problems. Zentralblatt MATH identifier Ma, Zongming; Wu, Yihong. Keywords Asymptotic equivalence high-dimensional statistics computational complexity minimax rate planted clique submatrix detection.

Yihong Wu — Information Theory Society

Ma, Zongming; Wu, Yihong. More by Zongming Ma Search this author in: 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. You have access to this content. You do not have access to this content.

  STPM 954 MATH T COURSEWORK 2014

Implications on the hardness of support recovery are also obtained. Computational barriers in minimax submatrix detection. Download Email Please enter a 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.

MR Digital Object Identifier: Article information Source Ann. This paper studies the minimax detection of yiihong small submatrix of elevated mean in a large matrix contaminated by additive Gaussian noise.

yihong wu thesis

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: 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.

References [1] Addario-Berry, L.

  HRCA ESSAY WRITING COMPETITION 2015 RESULTS

Yihong Wu :: ECE ILLINOIS

Computational and statistical boundaries for submatrix localization in a large noisy matrix Cai, T. More by Yihong Thsis Search this author in: You have partial access to this content. Google Scholar Project Euclid. Zentralblatt MATH identifier On combinatorial testing problems.

yihong wu thesis

December First available in Project Euclid: 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: More like this Computational and statistical boundaries for submatrix localization in a large noisy matrix Cai, T. Keywords Asymptotic equivalence high-dimensional statistics computational complexity minimax rate planted clique thesls detection.

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