Fast exact matrix completion: A unified optimization framework for matrix completion

Abstract

© 2020 Dimitris Bertsimas and Michael Lingzhi Li. License: CC-BY 4.0, see https://creativecommons.org/licenses/by/4.0/. Attribution requirements are provided at http://jmlr.org/papers/v21/19-471.html. 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.