Search Results for author:
Found 2 papers, 0 papers with code
Computationally Efficient and Statistically Optimal Robust High-Dimensional Linear Regression
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.
Computationally Efficient and Statistically Optimal Robust Low-rank Matrix and Tensor Estimation
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.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
