Inference of Online Newton Methods with Nesterov's Accelerated Sketching

ArXi:2604.23436v1 Announce Type: cross Reliable decision-making with streaming data requires principled uncertainty quantification of online methods. While first-order methods enable efficient iterate updates, their inference procedures still require updating proper (covariance) matrices, incurring $O(d^2)$ time and memory complexity, and are sensitive to ill-conditioning and noise heterogeneity of the problem. This costly inference task offers an opportunity for robust second-order methods, which are, however, bottlenecked by solving Newton systems with $O(d^3)$ complexity.