000			02101nam a22002057a 4500
003			OSt
005			20220107122853.0
008			190711b xxu||||| |||| 00| 0 eng d
040			_cIIITMK
100			_aVineetha K V (41718015) _916202
245			_aApplications of Matrix completion theory to image processing
300			_aMPhil CS 2018-2019
500			_aMatrix completion is the problem of recovering a low rank matrix from partially observed entries. It has been widely used in collaborative filtering and recommender systems, dimension reduction and multiclass learning. This area is a recently emerged field of study following the track of what has been explored in fields related to compressed sensing. Like in compressed sensing, matrix completion algorithms, therefore, involve reconstruction of the data matrix from a small subset of its noise corrupted entries. The missing entries can be recovered under certain conditions when the data matrix has a low rank. The conditions mainly stipulate that the number of available entries fall below a certain limit; and that some of the rows and columns of the matrix are completely unknown. There has been extensive work on designing efficient algorithms for matrix completion with guarantees. Earlier works on matrix completion were based on convex relaxations. These algorithms achieve strong statistical guarantees, but are quite computationally expensive in practice. More recently, there has been growing interest in analyzing non-convex algorithms for matrix completion. These algorithms are much faster than the convex relaxation algorithms, which is crucial for their empirical success in large-scale collaborative filtering applications. We compare both convex and non convex approaches for Matrix Completion. The results are generalized to the setting when the observed entries contain noise.
502			_bMPhil CS _c2018-2019 _dINT _eDr Joseph Suresh Paul
650			_aMatrix Completion _916203
650			_aData Matrix _916204
650			_a Low Rank Matrix _916205
650			_a Image Processing _916206
942			_2ddc _cPR
999			_c6576 _d6576