Matrix estimation by Universal Singular Value Thresholding
TLDR
This paper introduces a simple estimation procedure, called Universal Singular Value Thresholding (USVT), that works for any matrix that has "a little bit of structure" and achieves the minimax error rate up to a constant factor.Abstract:
Consider the problem of estimating the entries of a large matrix, when the observed entries are noisy versions of a small random fraction of the original entries. This problem has received widespread attention in recent times, especially after the pioneering works of Emmanuel Candes and collaborators. This paper introduces a simple estimation procedure, called Universal Singular Value Thresholding (USVT), that works for any matrix that has "a little bit of structure." Surprisingly, this simple estimator achieves the minimax error rate up to a constant factor. The method is applied to solve problems related to low rank matrix estimation, blockmodels, distance matrix completion, latent space models, positive definite matrix completion, graphon estimation and generalized Bradley--Terry models for pairwise comparison.read more
Citations
More filters
Journal ArticleDOI
The Optimal Hard Threshold for Singular Values is $4/\sqrt {3}$
Matan Gavish,David L. Donoho +1 more
TL;DR: Empirical evidence suggests that performance improvement over TSVD and other popular shrinkage rules can be substantial, for different noise distributions, even in relatively small n.
Journal ArticleDOI
Using Synthetic Controls: Feasibility, Data Requirements, and Methodological Aspects
TL;DR: Practical guidance is provided to researchers employing synthetic control methods and the advantages of the synthetic control framework as a research design, and the settings where synthetic controls provide reliable estimates and those where they may fail are described.
Posted Content
On Adaptive Attacks to Adversarial Example Defenses
TL;DR: In this article, the authors demonstrate that adaptive attacks can be circumvented despite attempting to perform evaluations using adaptive attacks, and provide guidance on how to properly perform adaptive attacks against defenses to adversarial examples, and thus allow the community to make further progress in building more robust models.
Journal ArticleDOI
Pseudo-likelihood methods for community detection in large sparse networks
TL;DR: It is proved that pseudo-likelihood provides consistent estimates of the communities under a mild condition on the starting value, for the case of a block model with two communities.
Posted Content
Generalized Low Rank Models
TL;DR: This work extends the idea of PCA to handle arbitrary data sets consisting of numerical, Boolean, categorical, ordinal, and other data types, and proposes several parallel algorithms for fitting generalized low rank models.
References
More filters
Book
Compressed sensing
TL;DR: It is possible to design n=O(Nlog(m)) nonadaptive measurements allowing reconstruction with accuracy comparable to that attainable with direct knowledge of the N most important coefficients, and a good approximation to those N important coefficients is extracted from the n measurements by solving a linear program-Basis Pursuit in signal processing.
Journal ArticleDOI
Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information
TL;DR: In this paper, the authors considered the model problem of reconstructing an object from incomplete frequency samples and showed that with probability at least 1-O(N/sup -M/), f can be reconstructed exactly as the solution to the lscr/sub 1/ minimization problem.
Journal ArticleDOI
Categorical Data Analysis
TL;DR: In this article, categorical data analysis was used for categorical classification of categorical categorical datasets.Categorical Data Analysis, categorical Data analysis, CDA, CPDA, CDSA
Journal ArticleDOI
A Singular Value Thresholding Algorithm for Matrix Completion
TL;DR: This paper develops a simple first-order and easy-to-implement algorithm that is extremely efficient at addressing problems in which the optimal solution has low rank, and develops a framework in which one can understand these algorithms in terms of well-known Lagrange multiplier algorithms.
Journal ArticleDOI
Exact Matrix Completion via Convex Optimization
TL;DR: It is proved that one can perfectly recover most low-rank matrices from what appears to be an incomplete set of entries, and that objects other than signals and images can be perfectly reconstructed from very limited information.