CUED Publications database

Scaled stochastic gradient descent for low-rank matrix completion

Mishra, B and Sepulchre, R (2016) Scaled stochastic gradient descent for low-rank matrix completion. In: IEEE 55th Conference on Decision and Control, CDC 2016, -- to -- pp. 2820-2825..

Full text not available from this repository.


© 2016 IEEE. The paper looks at a scaled variant of the stochastic gradient descent algorithm for the matrix completion problem. Specifically, we propose a novel matrix-scaling of the partial derivatives that acts as an efficient preconditioning for the standard stochastic gradient descent algorithm. This proposed matrix-scaling provides a trade-off between local and global second order information. It also resolves the issue of scale invariance that exists in matrix factorization models. The overall computational complexity is linear with the number of known entries, thereby extending to a large-scale setup. Numerical comparisons show that the proposed algorithm competes favorably with state-of-the-art algorithms on various different benchmarks.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Divisions: Div F > Control
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:13
Last Modified: 15 Apr 2021 06:41
DOI: 10.1109/CDC.2016.7798689