Provable Randomized Coordinate Descent for Matrix Completion
Published in IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2024
Here, we study a regularization-free randomized coordinate descent method that uses an efficient periodic refactorization to guarantee a linear convergence rate.
[Paper]Bibtex
@inproceedings{callahan2024provable,
title={Provable Randomized Coordinate Descent for Matrix Completion}, author={Callahan, Matthew and Vu, Trung and Raich, Raviv}, booktitle={ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, pages={9421--9425}, year={2024}, organization={IEEE} }