Back to Search
Start Over
Fast Exact Matrix Completion: A Unified Optimization Framework for Matrix Completion.
- Source :
-
Journal of Machine Learning Research . 2020, Vol. 20, p1-43. 43p. - Publication Year :
- 2020
-
Abstract
- We formulate the problem of matrix completion with and without side information as a non-convex optimization problem. We design fastImpute based on non-convex gradient descent and show it converges to a global minimum that is guaranteed to recover closely the underlying matrix while it scales to matrices of sizes beyond 105 × 105 . We report experiments on both synthetic and real-world datasets that show fastImpute is competitive in both the accuracy of the matrix recovered and the time needed across all cases. Furthermore, when a high number of entries are missing, fastImpute is over 75% lower in MAPE and 15 times faster than current state-of-the-art matrix completion methods in both the case with side information and without. [ABSTRACT FROM AUTHOR]
- Subjects :
- *MATRICES (Mathematics)
*STOCHASTIC approximation
Subjects
Details
- Language :
- English
- ISSN :
- 15324435
- Volume :
- 20
- Database :
- Academic Search Index
- Journal :
- Journal of Machine Learning Research
- Publication Type :
- Academic Journal
- Accession number :
- 151992190