Robust Matrix Completion and Corrupted Columns

104 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Data Poisoning Attacks on Factorization-Based Collaborative Filtering (2016, background): “In terms of collaborative filtering/matrix completion, there is another line of established research that focuses on robust matrix completion, in which a small portion of elements or rows in the underlying low-rank matrix is assumed to be arbitrarily perturbed [18, 19, 20, 21].”
Robust Linear Regression Against Training Data Poisoning (2017, methodology): “For each k , we evaluate the runtime of our algorithm along with the two baselines [11] and [30].”
Low-rank matrix recovery from errors and erasures (2011, methodology): “They arise in a variety of application areas, among them Principal Component Analysis (PCA) [1], [2], [3], Multi-dimensional scaling (MDS), Correlation Clustering [4], [5], Spectral Clustering and related methods [6], [7], ranking and collaborative filtering [8], [9], etc.”
Divide-and-Conquer Matrix Factorization (2011, background): “(7), we consider a sampling with batch replac ement scheme recommended in [9] and developed in [5].”
Robust Sparse Regression under Adversarial Corruption (2013, background): “, robust PCA and robust matrix completion (Chandrasekaran et al., 2011; Candes et al., 2009; Xu et al., 2012; Chen et al., 2011; Lerman et al., 2012), recent robust recovery in high dimensions results have for the most part depended on convex optimization formulations.”