D
David L. Donoho
Researcher at Stanford University
Publications - 273
Citations - 115802
David L. Donoho is an academic researcher from Stanford University. The author has contributed to research in topics: Wavelet & Compressed sensing. The author has an hindex of 110, co-authored 271 publications receiving 108027 citations. Previous affiliations of David L. Donoho include University of California, Berkeley & Western Geophysical.
Papers
More filters
Journal ArticleDOI
Minimax risk of matrix denoising by singular value thresholding
David L. Donoho,Matan Gavish +1 more
Abstract: An unknown $m$ by $n$ matrix $X_0$ is to be estimated from noisy measurements $Y=X_0+Z$, where the noise matrix $Z$ has i.i.d. Gaussian entries. A popular matrix denoising scheme solves the nuclear norm penalization problem $\operatorname {min}_X\|Y-X\|_F^2/2+\lambda\|X\|_*$, where $\|X\|_*$ denotes the nuclear norm (sum of singular values). This is the analog, for matrices, of $\ell_1$ penalization in the vector case. It has been empirically observed that if $X_0$ has low rank, it may be recovered quite accurately from the noisy measurement $Y$. In a proportional growth framework where the rank $r_n$, number of rows $m_n$ and number of columns $n$ all tend to $\infty$ proportionally to each other ($r_n/m_n\rightarrow \rho$, $m_n/n\rightarrow \beta$), we evaluate the asymptotic minimax MSE $\mathcal {M}(\rho,\beta)=\lim_{m_n,n\rightarrow \infty}\inf_{\lambda}\sup_{\operatorname {rank}(X)\leq r_n}\operatorname {MSE}(X_0,\hat{X}_{\lambda})$. Our formulas involve incomplete moments of the quarter- and semi-circle laws ($\beta=1$, square case) and the Marcenko-Pastur law ($\beta<1$, nonsquare case). For finite $m$ and $n$, we show that MSE increases as the nonzero singular values of $X_0$ grow larger. As a result, the finite-$n$ worst-case MSE, a quantity which can be evaluated numerically, is achieved when the signal $X_0$ is "infinitely strong." The nuclear norm penalization problem is solved by applying soft thresholding to the singular values of $Y$. We also derive the minimax threshold, namely the value $\lambda^*(\rho)$, which is the optimal place to threshold the singular values. All these results are obtained for general (nonsquare, nonsymmetric) real matrices. Comparable results are obtained for square symmetric nonnegative-definite matrices.
Journal ArticleDOI
Deterministic matrices matching the compressed sensing phase transitions of Gaussian random matrices
Hatef Monajemi,Sina Jafarpour,Matan Gavish,Stat,David L. Donoho,Sivaram Ambikasaran,Sergio Bacallado,Dinesh Bharadia,Yuxin Chen,Young Ki Choi,Mainak Chowdhury,Soham Chowdhury,Anil Damle,Will Fithian,Georges Goetz,Logan Grosenick,Samuel R. Gross,Gage Hills,Michael Hornstein,Milinda Lakkam,Jason D. Lee,Jian Li,Linxi Liu,Carlos Sing-Long,Michael Marx,Akshay Mittal,Albert No,Reza Omrani,Leonid Pekelis,Junjie Qin,Kevin S. Raines,Ernest K. Ryu,Andrew M. Saxe,Dai Shi,Keith Siilats,David Strauss,Gary Tang,Chaojun Wang,Zoey Zhou,Zhen Zhu +39 more
TL;DR: It is observed that convex optimization is successful over a region of the phase diagram that coincides with the region known for Gaussian random matrices, and this finding is established for each of the four associated phase transitions.
Journal ArticleDOI
Microlocal Analysis of the Geometric Separation Problem
David L. Donoho,Gitta Kutyniok +1 more
TL;DR: In this paper, the authors present a theoretical analysis showing that accurate geometric separation of point and curve singularities can be achieved by minimizing the 1 norm of the representing coefficients in two geometrically complementary frames: wavelets and curvelets.
Wavelet Shrinkage and W.V.D.: A 10-minute tour
TL;DR: In this article, the authors presented at the International Conference on Wavelets and Applications, Toulouse, France, June, 1992, based on presentation at the NSF DMS 92-09130.
Journal ArticleDOI
Higher Criticism for Large-Scale Inference: especially for Rare and Weak effects
David L. Donoho,Jiashun Jin +1 more
TL;DR: The Rare/Weak (RW) model is a theoretical framework simultaneously controlling the size and prevalence of useful/significant items among the useless/null bulk, and shows that HC has important advantages over better known procedures such as False Discovery Rate (FDR) control and Family-wise Error control (FwER), in particular, certain optimality properties.