Skip to content
#

denoised-gradient-estimation

Here is 1 public repository matching this topic...

A memory-efficient, gradient-free zeroth-order (derivative-free) optimizer designed to solve the "Curse of Dimensionality" in Black-Box optimization and memory-constrained Machine Learning. It provides an O(log D) gradient estimation approach that can successfully train Neural Networks without ever calculating analytical derivatives or Backprop

  • Updated Aug 7, 2026
  • Python

Add this topic to your repo

To associate your repository with the denoised-gradient-estimation topic, visit your repo's landing page and select "manage topics."

Learn more