Matrix Approximation under Local Low-Rank Assumption
Venue
The Learning Workshop in International Conference on Learning Representations (ICLR) (2013)
Publication Year
2013
Authors
Joonseok Lee, Seungyeon Kim, Guy Lebanon, Yoram Singer
BibTeX
Abstract
Matrix approximation is a common tool in machine learning for building accurate
prediction models for recommendation systems, text mining, and computer vision. A
prevalent assumption in constructing matrix approximations is that the partially
observed matrix is of low-rank. We propose a new matrix approximation model where
we assume instead that the matrix is only locally of low-rank, leading to a
representation of the observed matrix as a weighted sum of low-rank matrices. We
analyze the accuracy of the proposed local low-rank modeling. Our experiments show
improvements of prediction accuracy in recommendation tasks.
