We have located links that may give you full text access.
JOURNAL ARTICLE
RESEARCH SUPPORT, AMERICAN RECOVERY AND REINVESTMENT ACT
RESEARCH SUPPORT, NON-U.S. GOV'T
RESEARCH SUPPORT, U.S. GOV'T, NON-P.H.S.
The phase transition of matrix recovery from Gaussian measurements matches the minimax MSE of matrix denoising.
Let X(0) be an unknown M by N matrix. In matrix recovery, one takes n < MN linear measurements y(1),…,y(n) of X(0), where y(i) = Tr(A(T)iX(0)) and each A(i) is an M by N matrix. A popular approach for matrix recovery is nuclear norm minimization (NNM): solving the convex optimization problem min ||X||*subject to y(i) =Tr(A(T)(i)X) for all 1 ≤ i ≤ n, where || · ||* denotes the nuclear norm, namely, the sum of singular values. Empirical work reveals a phase transition curve, stated in terms of the undersampling fraction δ(n,M,N) = n/(MN), rank fraction ρ=rank(X0)/min {M,N}, and aspect ratio β=M/N. Specifically when the measurement matrices Ai have independent standard Gaussian random entries, a curve δ*(ρ) = δ*(ρ;β) exists such that, if δ > δ*(ρ), NNM typically succeeds for large M,N, whereas if δ < δ*(ρ), it typically fails. An apparently quite different problem is matrix denoising in Gaussian noise, in which an unknown M by N matrix X(0) is to be estimated based on direct noisy measurements Y =X(0) + Z, where the matrix Z has independent and identically distributed Gaussian entries. A popular matrix denoising scheme solves the unconstrained optimization problem min|| Y-X||(2)(F)/2+λ||X||*. When optimally tuned, this scheme achieves the asymptotic minimax mean-squared error M(ρ;β) = lim(M,N → ∞)inf(λ)sup(rank(X) ≤ ρ · M)MSE(X,X(λ)), where M/N → . We report extensive experiments showing that the phase transition δ*(ρ) in the first problem, matrix recovery from Gaussian measurements, coincides with the minimax risk curve M(ρ)=M(ρ;β) in the second problem, matrix denoising in Gaussian noise: δ*(ρ)=M(ρ), for any rank fraction 0 < ρ < 1 (at each common aspect ratio β). Our experiments considered matrices belonging to two constraint classes: real M by N matrices, of various ranks and aspect ratios, and real symmetric positive-semidefinite N by N matrices, of various ranks.
Full text links
Related Resources
Get seemless 1-tap access through your institution/university
For the best experience, use the Read mobile app
All material on this website is protected by copyright, Copyright © 1994-2024 by WebMD LLC.
This website also contains material copyrighted by 3rd parties.
By using this service, you agree to our terms of use and privacy policy.
Your Privacy Choices
You can now claim free CME credits for this literature searchClaim now
Get seemless 1-tap access through your institution/university
For the best experience, use the Read mobile app