Truncated Matrix Completion - An Empirical Study
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908317565059072 |
|---|---|
| author | Naik, Rishhabh Trivedi, Nisarg Tarzanagh, Davoud Ataee Balzano, Laura |
| author_facet | Naik, Rishhabh Trivedi, Nisarg Tarzanagh, Davoud Ataee Balzano, Laura |
| contents | Low-rank Matrix Completion (LRMC) describes the problem where we wish to recover missing entries of partially observed low-rank matrix. Most existing matrix completion work deals with sampling procedures that are independent of the underlying data values. While this assumption allows the derivation of nice theoretical guarantees, it seldom holds in real-world applications. In this paper, we consider various settings where the sampling mask is dependent on the underlying data values, motivated by applications in sensing, sequential decision-making, and recommender systems. Through a series of experiments, we study and compare the performance of various LRMC algorithms that were originally successful for data-independent sampling patterns. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_09873 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Truncated Matrix Completion - An Empirical Study Naik, Rishhabh Trivedi, Nisarg Tarzanagh, Davoud Ataee Balzano, Laura Machine Learning Artificial Intelligence Numerical Analysis Low-rank Matrix Completion (LRMC) describes the problem where we wish to recover missing entries of partially observed low-rank matrix. Most existing matrix completion work deals with sampling procedures that are independent of the underlying data values. While this assumption allows the derivation of nice theoretical guarantees, it seldom holds in real-world applications. In this paper, we consider various settings where the sampling mask is dependent on the underlying data values, motivated by applications in sensing, sequential decision-making, and recommender systems. Through a series of experiments, we study and compare the performance of various LRMC algorithms that were originally successful for data-independent sampling patterns. |
| title | Truncated Matrix Completion - An Empirical Study |
| topic | Machine Learning Artificial Intelligence Numerical Analysis |
| url | https://arxiv.org/abs/2504.09873 |