How many neurons do we need? A refined analysis for shallow networks trained with gradient descent

DOI10.1016/j.jspi.2024.106169MaRDI QIDQ6592785

Nicole Mücke, Mike Nguyen

Publication date: 26 August 2024

Published in: Journal of Statistical Planning and Inference (Search for Journal in Brave)

zbMATH Keywords

gradient descentearly stoppingneural tangent kernel

Mathematics Subject Classification ID

Statistics (62-XX)

Cites Work

• Unnamed Item
• Optimal rates for regularization of statistical inverse learning problems
• Gradient descent optimizes over-parameterized deep ReLU networks
• Optimal rates for the regularized least-squares algorithm
• Support Vector Machines
• Mathematical Statistics
• Spurious Valleys in Two-layer Neural Network Optimization Landscapes

This page was built for publication: How many neurons do we need? A refined analysis for shallow networks trained with gradient descent