ICML 2024 "over-parameterized networks" Papers
3 papers found
How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers
Gon Buzaglo, Itamar Harel, Mor Shpigel Nacson et al.
ICML 2024spotlightarXiv:2402.06323
Memorization Through the Lens of Curvature of Loss Function Around Samples
Isha Garg, Deepak Ravikumar, Kaushik Roy
ICML 2024spotlightarXiv:2307.05831
When Will Gradient Regularization Be Harmful?
Yang Zhao, Hao Zhang, Xiuyuan Hu
ICML 2024posterarXiv:2406.09723