Recovering Quantized Data with Missing Information Using Bilinear Factorization and Augmented Lagrangian Method
Machine Learning
2018-10-09 v1 Machine Learning
Abstract
In this paper, we propose a novel approach in order to recover a quantized matrix with missing information. We propose a regularized convex cost function composed of a log-likelihood term and a Trace norm term. The Bi-factorization approach and the Augmented Lagrangian Method (ALM) are applied to find the global minimizer of the cost function in order to recover the genuine data. We provide mathematical convergence analysis for our proposed algorithm. In the Numerical Experiments Section, we show the superiority of our method in accuracy and also its robustness in computational complexity compared to the state-of-the-art literature methods.
Cite
@article{arxiv.1810.03222,
title = {Recovering Quantized Data with Missing Information Using Bilinear Factorization and Augmented Lagrangian Method},
author = {Ashkan Esmaeili and Kayhan Behdin and Sina Al-E-Mohammad and Farokh Marvasti},
journal= {arXiv preprint arXiv:1810.03222},
year = {2018}
}