Convergence Rate for the Last Iterate of Stochastic Gradient Descent Schemes
arXiv:2507.07281v4 Announce Type: replace-cross Abstract: 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 gr...
🔗 Read more: https://arxiv.org/abs/2507.07281
#News #Math #WorldNews #Policy #Academic
Edited
Comments
Log in to leave a comment.
No comments yet. Be the first to comment!