AI RESEARCH
Convergence Rate for the Last Iterate of Stochastic Gradient Descent Schemes
arXiv CS.LG
•
ArXi:2507.07281v4 Announce Type: replace-cross We study the convergence rate for the last iterate of stochastic gradient descent (SGD) and stochastic heavy ball (SHB) in the parametric setting when the objective function $F$ is globally convex or non-convex whose gradient is $\gamma$-H\"{o}lder.