NeurIPS "overparameterized models" Papers
3 papers found
Adam Reduces a Unique Form of Sharpness: Theoretical Insights Near the Minimizer Manifold
Xinghan Li, Haodong Wen, Kaifeng Lyu
NeurIPS 2025posterarXiv:2511.02773
Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining
Nathan Stromberg, Christos Thrampoulidis, Lalitha Sankar
NeurIPS 2025posterarXiv:2506.20025
1
citations
Why Diffusion Models Don’t Memorize: The Role of Implicit Dynamical Regularization in Training
Tony Bonnaire, Raphaël Urfin, Giulio Biroli et al.
NeurIPS 2025oral