ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1309.5914
39
149

Computational barriers in minimax submatrix detection

23 September 2013
Zongming Ma
Yihong Wu
ArXivPDFHTML
Abstract

This paper studies the minimax detection of a small submatrix of elevated mean in a large matrix contaminated by additive Gaussian noise. 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. 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: when the size of the large matrix p→∞p\to\inftyp→∞, if the submatrix size k=Θ(pα)k=\Theta(p^{\alpha})k=Θ(pα) for any α∈(0,2/3)\alpha\in(0,{2}/{3})α∈(0,2/3), computational complexity constraints can incur a severe penalty on the statistical performance in the sense that any randomized polynomial-time test is minimax suboptimal by a polynomial factor in ppp; if k=Θ(pα)k=\Theta(p^{\alpha})k=Θ(pα) for any α∈(2/3,1)\alpha\in({2}/{3},1)α∈(2/3,1), minimax optimal detection can be attained within constant factors in linear time. 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.

View on arXiv
Comments on this paper