ICML "gradient descent dynamics" Papers
4 papers found
A Dynamical Model of Neural Scaling Laws
Blake Bordelon, Alexander Atanasov, Cengiz Pehlevan
ICML 2024poster
A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks
Behrad Moniri, Donghwan Lee, Hamed Hassani et al.
ICML 2024poster
The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents
Yatin Dandi, Emanuele Troiani, Luca Arnaboldi et al.
ICML 2024poster
Why Do You Grok? A Theoretical Analysis on Grokking Modular Addition
Mohamad Amin Mohamadi, Zhiyuan Li, Lei Wu et al.
ICML 2024poster