ResearchTrend.AI
Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization

Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization

Hancheng Min
Enrique Mallada
René Vidal
    MLT
ArXivPDFHTML

Papers citing "Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization"

6 / 6 papers shown
Title
Directional Convergence, Benign Overfitting of Gradient Descent in leaky ReLU two-layer Neural Networks
Directional Convergence, Benign Overfitting of Gradient Descent in leaky ReLU two-layer Neural Networks
Ichiro Hashimoto
MLT
30
0
0
22 May 2025
Early Directional Convergence in Deep Homogeneous Neural Networks for Small Initializations
Early Directional Convergence in Deep Homogeneous Neural Networks for Small Initializations
Akshay Kumar
Jarvis Haupt
ODL
49
3
0
12 Mar 2024
Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction
Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction
Dominik Stöger
Mahdi Soltanolkotabi
ODL
56
75
0
28 Jun 2021
Gradient Descent Maximizes the Margin of Homogeneous Neural Networks
Gradient Descent Maximizes the Margin of Homogeneous Neural Networks
Kaifeng Lyu
Jian Li
68
332
0
13 Jun 2019
Implicit Regularization in Deep Matrix Factorization
Implicit Regularization in Deep Matrix Factorization
Sanjeev Arora
Nadav Cohen
Wei Hu
Yuping Luo
AI4CE
61
500
0
31 May 2019
Gradient Descent Quantizes ReLU Network Features
Gradient Descent Quantizes ReLU Network Features
Hartmut Maennel
Olivier Bousquet
Sylvain Gelly
MLT
28
80
0
22 Mar 2018