no code implementations • 10 May 2023 • Yinan Shen, Jingyang Li, Jian-Feng Cai, Dong Xia
The algorithm is not only computationally efficient with linear convergence but also statistically optimal, be the noise Gaussian or heavy-tailed with a finite 1 + epsilon moment.
no code implementations • 2 Mar 2022 • Yinan Shen, Jingyang Li, Jian-Feng Cai, Dong Xia
Lastly, RsGrad is applicable for low-rank tensor estimation under heavy-tailed noise where a statistically optimal rate is attainable with the same phenomenon of dual-phase convergence, and a novel shrinkage-based second-order moment method is guaranteed to deliver a warm initialization.