688 citations · 1.9k across the 57 of their papers we have counts for
5 papers · 1 filter
Non-convex Robust PCA
Praneeth Netrapalli, U N Niranjan, Sujay Sanghavi +2
We propose a new method for robust PCA -- the task of recovering a low-rank matrix from sparse corruptions that are of unknown value and support. Our method involves alternating be…
Low-rank Matrix Recovery from Errors and Erasures
Yudong Chen, Ali Jalali, Sujay Sanghavi +1
This paper considers the recovery of a low-rank matrix from an observed version that simultaneously contains both (a) erasures: most entries are not observed, and (b) errors: value…
Sequential Compressed Sensing
Dmitry Malioutov, Sujay Sanghavi, Alan Willsky
Compressed sensing allows perfect recovery of sparse signals (or signals sparse in some basis) using only a small number of random measurements. Existing results in compressed sens…
Equivalence of LP Relaxation and Max-Product for Weighted Matching in General Graphs
Sujay Sanghavi
Max-product belief propagation is a local, iterative algorithm to find the mode/MAP estimate of a probability distribution. While it has been successfully employed in a wide variet…
Intermediate Performance of Rateless Codes
Sujay Sanghavi
Rateless/fountain codes are designed so that all input symbols can be recovered from a slightly larger number of coded symbols, with high probability using an iterative decoder. In…