Computational Barriers in Minimax Submatrix Detection
نویسندگان
چکیده
This paper studies the minimax detection of a small submatrix of elevated mean in a p× p matrix contaminated by additive Gaussian noise where p tends to infinity. 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 in the sense of Le Cam. 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: If the submatrix size k = Θ(pα) for any 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 k; If k = Θ(pα) for any 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 depends on the loss function. Implications on the hardness of support recovery are also discussed.
منابع مشابه
Computational and Statistical Boundaries for Submatrix Localization in a Large Noisy
We study in this paper computational and statistical boundaries for submatrix localization. Given one observation of (one or multiple non-overlapping) signal submatrix (of magnitude λ and size km×kn) embedded in a large noise matrix (of size m × n), the goal is to optimal identify the support of the signal submatrix computationally and statistically. Two transition thresholds for the signal to ...
متن کاملStatistical-Computational Tradeoffs in Planted Problems and Submatrix Localization with a Growing Number of Clusters and Submatrices
We consider two closely related problems: planted clustering and submatrix localization. In the planted clustering problem, a random graph is generated based on an underlying cluster structure of the nodes; the task is to recover these clusters given the graph. The submatrix localization problem concerns locating hidden submatrices with elevated means inside a large real-valued random matrix. O...
متن کاملComputational aspect to the nearest southeast submatrix that makes multiple a prescribed eigenvalue
Given four complex matrices $A$, $B$, $C$ and $D$ where $Ainmathbb{C}^{ntimes n}$ and $Dinmathbb{C}^{mtimes m}$ and let the matrix $left(begin{array}{cc} A & B C & D end{array} right)$ be a normal matrix and assume that $lambda$ is a given complex number that is not eigenvalue of matrix $A$. We present a method to calculate the distance norm (with respect to 2-norm) from $D$ to ...
متن کاملSparse CCA: Adaptive Estimation and Computational Barriers
Canonical correlation analysis (CCA) is a classical and important multivariate technique for exploring the relationship between two sets of variables. It has applications in many fields including genomics and imaging, to extract meaningful features as well as to use the features for subsequent analysis. This paper considers adaptive and computationally tractable estimation of leading sparse can...
متن کاملRobust multiuser detection in impulsive channels based on M-estimation using a new penalty function
Introduction: Detection and estimation theory is one of the core investigation areas in communications. Multiuser detection (MUD) is an estimation problem in which different users transmit their signals through the same channel in a multiple access channel (MAC). In this way the receiver explores desired signal through the ambient noise and interference generated by other user signals. Multiuse...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1309.5914 شماره
صفحات -
تاریخ انتشار 2013