132 citations · 305 across the 14 of their papers we have counts for
19 papers
Ranking of Multi-Response Experiment Treatments
Miguel R. Pebes-Trujillo, Itamar Shenhar, Aravind Harikumar +4
We present a probabilistic ranking model to identify the optimal treatment in multiple-response experiments. In contemporary practice, treatments are applied over individuals with…
Matrix Denoising with Partial Noise Statistics: Optimal Singular Value Shrinkage of Spiked F-Matrices
Matan Gavish, William Leeb, Elad Romanov
We study the problem of estimating a large, low-rank matrix corrupted by additive noise of unknown covariance, assuming one has access to additional side information in the form of…
Asymptotic Frame Theory for Analog Coding
Marina Haikin, Matan Gavish, Dustin G. Mixon +1
Over-complete systems of vectors, or in short, frames, play the role of analog codes in many areas of communication and signal processing. To name a few, spreading sequences for co…
ScreeNOT: Exact MSE-Optimal Singular Value Thresholding in Correlated Noise
David L. Donoho, Matan Gavish, Elad Romanov
We derive a formula for optimal hard thresholding of the singular value decomposition in the presence of correlated additive noise; although it nominally involves unobservables, we…
LOCA: LOcal Conformal Autoencoder for standardized data coordinates
Erez Peterfreund, Ofir Lindenbaum, Felix Dietrich +4
We propose a deep-learning based method for obtaining standardized data coordinates from scientific measurements.Data observations are modeled as samples from an unknown, non-linea…
Optimal Recovery of Precision Matrix for Mahalanobis Distance from High Dimensional Noisy Observations in Manifold Learning
Matan Gavish, Ronen Talmon, Pei-Chun Su +1
Motivated by establishing theoretical foundations for various manifold learning algorithms, we study the problem of Mahalanobis distance (MD), and the associated precision matrix,…
The Noise-Sensitivity Phase Transition in Spectral Group Synchronization Over Compact Groups
Elad Romanov, Matan Gavish
In Group Synchronization, one attempts to find a collection of unknown group elements from noisy measurements of their pairwise differences. Several important problems in vision an…
Multidimensional Scaling of Noisy High Dimensional Data
Erez Peterfreund, Matan Gavish
Multidimensional Scaling (MDS) is a classical technique for embedding data in low dimensions, still in widespread use today. Originally introduced in the 1950's, MDS was not design…
Frame Moments and Welch Bound with Erasures
Marina Haikin, Ram Zamir, Matan Gavish
The Welch Bound is a lower bound on the root mean square cross correlation between unit-norm vectors in the dimensional space ( or $\mathbb{C}…
Optimal Shrinkage of Singular Values Under Random Data Contamination
Danny Barash, Matan Gavish
A low rank matrix X has been contaminated by uniformly distributed noise, missing values, outliers and corrupt entries. Reconstruction of X from the singular values and singular ve…
ReFACTor: Practical Low-Rank Matrix Estimation Under Column-Sparsity
Matan Gavish, Regev Schweiger, Elior Rahmani +1
Various problems in data analysis and statistical genetics call for recovery of a column-sparse, low-rank matrix from noisy observations. We propose ReFACTor, a simple variation of…
Near-optimal matrix recovery from random linear measurements
Elad Romanov, Matan Gavish
In matrix recovery from random linear measurements, one is interested in recovering an unknown -by- matrix from measurements where each …
Random Subsets of Structured Deterministic Frames have MANOVA Spectra
Marina Haikin, Ram Zamir, Matan Gavish
We draw a random subset of rows from a frame with rows (vectors) and columns (dimensions), where and are proportional to . For a variety of important determi…
Optimal Shrinkage of Singular Values
Matan Gavish, David L. Donoho
We consider recovery of low-rank matrices from noisy data by shrinkage of singular values, in which a single, univariate nonlinearity is applied to each of the empirical singular v…
The Maximum Entropy Relaxation Path
Moshe Dubiner, Matan Gavish, Yoram Singer
The relaxed maximum entropy problem is concerned with finding a probability distribution on a finite set that minimizes the relative entropy to a given prior distribution, while sa…
Optimal Shrinkage of Eigenvalues in the Spiked Covariance Model
David L. Donoho, Matan Gavish, Iain M. Johnstone
We show that in a common high-dimensional covariance model, the choice of loss function has a profound effect on optimal estimation. In an asymptotic framework based on the Spiked…
The Optimal Hard Threshold for Singular Values is 4/sqrt(3)
Matan Gavish, David L. Donoho
We consider recovery of low-rank matrices from noisy data by hard thresholding of singular values, where singular values below a prescribed threshold are set to 0. We study the…
Minimax risk of matrix denoising by singular value thresholding
David Donoho, Matan Gavish
An unknown by matrix is to be estimated from noisy measurements , where the noise matrix has i.i.d. Gaussian entries. A popular matrix denoising scheme s…
The Phase Transition of Matrix Recovery from Gaussian Measurements Matches the Minimax MSE of Matrix Denoising
David L. Donoho, Matan Gavish, Andrea Montanari
Let be an unknown by matrix. In matrix recovery, one takes linear measurements of , where $y_i = \Tr(a_i^T X_0)$ and each is a …