AI RESEARCH

Online Covariance Matrix Estimation in Sketched Newton Methods

arXiv CS.LG

ArXi:2502.07114v2 Announce Type: replace-cross Given the ubiquity of streaming data, online algorithms have been widely used for parameter estimation, with second-order methods particularly standing out for their efficiency and robustness. In this paper, we study an online sketched Newton method that leverages a randomized sketching technique to perform an approximate Newton step in each iteration, thereby eliminating the computational bottleneck of second-order methods.