621bf66ddb7c962aa0d22ac97d69b793-Reviews.html

The authors propose a method (SHRT) to accelerate Ridge Regression when the number of features p is much greater than the number of samples n (p n). The main idea is to reduce the dimensionality of the design input matrix X to make the computation of XX T faster, from O(n 2) to O(nplogn). This is done via Walsh-Hadamard transforms, which can be computed in log-time. The research idea is of high-quality and great use. The paper is well written and technically correct.