Please use this identifier to cite or link to this item:
Title: Robust matrix completion and corrupted columns
Authors: Chen, Y.
Xu, H. 
Caramanis, C.
Sanghavi, S.
Issue Date: 2011
Citation: Chen, Y.,Xu, H.,Caramanis, C.,Sanghavi, S. (2011). Robust matrix completion and corrupted columns. Proceedings of the 28th International Conference on Machine Learning, ICML 2011 : 873-880. ScholarBank@NUS Repository.
Abstract: This paper considers the problem of matrix completion, when some number of the columns are arbitrarily corrupted. It is well-known that standard algorithms for matrix completion can return arbitrarily poor results, if even a single column is corrupted. What can be done if a large number, or even a constant fraction of columns are corrupted? In this paper, we study this very problem, and develop an robust and efficient algorithm for its solution. One direct application comes from robust collaborative filtering. Here, some number of users are so-called manipulators, and try to skew the predictions of the algorithm. Significantly, our results hold without any assumptions on the observed entries of the manipulated columns. Copyright 2011 by the author(s)/owner(s).
Source Title: Proceedings of the 28th International Conference on Machine Learning, ICML 2011
ISBN: 9781450306195
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

checked on Sep 14, 2018

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.