Neural Networks Trained by Weight Permutation are Universal Approximators

1 July 2024

Papers citing "Neural Networks Trained by Weight Permutation are Universal Approximators"

4 / 4 papers shown

Title
From Task-Specific Models to Unified Systems: A Review of Model Merging Approaches Wei Ruan Tianze Yang Y. Zhou Tianming Liu Jin Lu MoMe 88 0 0 13 Mar 2025
Git Re-Basin: Merging Models modulo Permutation Symmetries Samuel K. Ainsworth J. Hayase S. Srinivasa MoMe 239 313 0 11 Sep 2022
Optimal Approximation Rate of ReLU Networks in terms of Width and Depth Zuowei Shen Haizhao Yang Shijun Zhang 79 114 0 28 Feb 2021
Benefits of depth in neural networks Matus Telgarsky 121 600 0 14 Feb 2016