Poster "two-layer networks" Papers
5 papers found
Conference
A Minimalist Example of Edge-of-Stability and Progressive Sharpening
Liming Liu, Zixuan Zhang, Simon Du et al.
NEURIPS 2025arXiv:2503.02809
1
citations
Benign Overfitting in Adversarial Training of Neural Networks
Yunjuan Wang, Kaibo Zhang, Raman Arora
ICML 2024
Simplicity Bias of Two-Layer Networks beyond Linearly Separable Data
Nikita Tsoy, Nikola Konstantinov
ICML 2024arXiv:2405.17299
11
citations
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 2024arXiv:2402.03220
39
citations
Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural Networks
Stefano Mannelli, Yaraslau Ivashynka, Andrew Saxe et al.
ICML 2024arXiv:2406.01589
9
citations