NeurIPS "gradient descent analysis" Papers
2 papers found
Benign Overfitting in Single-Head Attention
Roey Magen, Shuning Shang, Zhiwei Xu et al.
NeurIPS 2025posterarXiv:2410.07746
6
citations
When majority rules, minority loses: bias amplification of gradient descent
François Bachoc, Jerome Bolte, Ryan Boustany et al.
NeurIPS 2025posterarXiv:2505.13122
1
citations