NoisyCUR: An Algorithm for Two-Cost Budgeted Matrix Completion

• Published in: Machine Learning and Knowledge Discovery in Databases Vol. 12457; pp. 746 - 761
• Main Authors: Hu, Dong, Gittens, Alex, Magdon-Ismail, Malik
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2021; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Low-rank approximation; Matrix completion; Nuclear norm minimization

Matrix completion is a ubiquitous tool in machine learning and data analysis. Most work in this area has focused on the number of observations necessary to obtain an accurate low-rank approximation. In practice, however, the cost of observations is an important limiting factor, and experimentalists...