KH-SGD iteratively reorders datapoints during stochastic gradient descent training to provably accelerate convergence.
-
Updated
Jul 8, 2025 - Jupyter Notebook
KH-SGD iteratively reorders datapoints during stochastic gradient descent training to provably accelerate convergence.
Add a description, image, and links to the kernel-halving topic page so that developers can more easily learn about it.
To associate your repository with the kernel-halving topic, visit your repo's landing page and select "manage topics."