Announcement_30_icml2025

Created in April 30, 2026

2026

Adnan Mohammed’s paper, “SparseOpt: Addressing Normalization-induced Gradient Skew in Sparse Training” (Adnan et al., 2026), has been accepted at the International Conference on Machine Learning (ICML), 2026. This work introduces SparseOpt, a novel optimization algorithm designed to mitigate the issue of gradient skew caused by normalization in sparse training. SparseOpt effectively balances the gradient updates across all parameters, leading to improved convergence and performance in sparse neural networks.



Enjoy Reading This Article?

Here are some more articles you might like to read next:

  • Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight Symmetry
  • Beyond Compression: How Knowledge Distillation Impacts Fairness and Bias in AI Models
  • Dynamic Sparse Training with Structured Sparsity
  • Gradient Flow in Sparse Neural Networks & Why Lottery Tickets Win