Matrix Completion under Interval Uncertainty
Optimization and Control
2018-02-20 v2 Artificial Intelligence
Information Retrieval
Abstract
Matrix completion under interval uncertainty can be cast as matrix completion with element-wise box constraints. We present an efficient alternating-direction parallel coordinate-descent method for the problem. We show that the method outperforms any other known method on a benchmark in image in-painting in terms of signal-to-noise ratio, and that it provides high-quality solutions for an instance of collaborative filtering with 100,198,805 recommendations within 5 minutes.
Cite
@article{arxiv.1408.2467,
title = {Matrix Completion under Interval Uncertainty},
author = {Jakub Marecek and Peter Richtarik and Martin Takac},
journal= {arXiv preprint arXiv:1408.2467},
year = {2018}
}