Directional Convergence Near Small Initializations and Saddles in Two-Homogeneous Neural Networks

14 February 2024

Papers citing "Directional Convergence Near Small Initializations and Saddles in Two-Homogeneous Neural Networks"

7 / 7 papers shown

Title
An overview of condensation phenomenon in deep learning Zhi-Qin John Xu Yaoyu Zhang Zhangchen Zhou AI4CE 24 0 0 13 Apr 2025
Simplicity bias and optimization threshold in two-layer ReLU networks Etienne Boursier Nicolas Flammarion 24 2 0 03 Oct 2024
Can Implicit Bias Imply Adversarial Robustness? Hancheng Min René Vidal 24 3 0 24 May 2024
Early Directional Convergence in Deep Homogeneous Neural Networks for Small Initializations Akshay Kumar Jarvis D. Haupt ODL 42 3 0 12 Mar 2024
Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding Zhengqing Wu Berfin Simsek Francois Ged ODL 32 0 0 08 Feb 2024
Phase Diagram of Initial Condensation for Two-layer Neural Networks Zheng Chen Yuqing Li Tao Luo Zhaoguang Zhou Z. Xu MLT AI4CE 39 8 0 12 Mar 2023
On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias Itay Safran Gal Vardi Jason D. Lee MLT 41 23 0 18 May 2022