AI RESEARCH
Last-Iterate Convergence of Randomized Kaczmarz and SGD with Greedy Step Size
arXiv CS.LG
•
ArXi:2604.09909v1 Announce Type: new We study last-iterate convergence of SGD with greedy step size over smooth quadratics in the interpolation regime, a setting which captures the classical Randomized Kaczmarz algorithm as well as other popular iterative linear system solvers. For these methods, we show that the $t$-th iterate attains an $O(1/t^{3/4})$ convergence rate, addressing a question posed by Attia, Schliserman, Sherman, and Koren, who gave an $O(1/t^{1/2})$ guarantee for this setting. In the proof, we.