ICML 2024 "two-layer networks" Papers
5 papers found
Asymptotics of feature learning in two-layer networks after one gradient-step
Hugo Cui, Luca Pesce, Yatin Dandi et al.
ICML 2024spotlight
Benign Overfitting in Adversarial Training of Neural Networks
Yunjuan Wang, Kaibo Zhang, Raman Arora
ICML 2024poster
Simplicity Bias of Two-Layer Networks beyond Linearly Separable Data
Nikita Tsoy, Nikola Konstantinov
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
Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural Networks
Stefano Mannelli, Yaraslau Ivashynka, Andrew Saxe et al.
ICML 2024poster