Provable Randomized Coordinate Descent for Matrix Completion
Published in ICASSP, 2024
Here, we study a regularization-free randomized coordinate descent method that uses an efficient periodic refactorization to guarantee a linear convergence rate.
Recommended citation: M. Callahan, T. Vu and R. Raich, "Provable Randomized Coordinate Descent for Matrix Completion," ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Korea, Republic of, 2024, pp. 9421-9425, doi: 10.1109/ICASSP48485.2024.10446340.