On the Implicit Bias Towards Minimal Depth of Deep Neural Networks

18 February 2022

Papers citing "On the Implicit Bias Towards Minimal Depth of Deep Neural Networks"

6 / 6 papers shown

Title
Feature learning is decoupled from generalization in high capacity neural networks Niclas Goring Charles London Abdurrahman Hadi Erturk Chris Mingard Yoonsoo Nam Ard A. Louis OOD MLT 224 1 0 25 Jul 2025
Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers Peter Súkeník Christoph H. Lampert Marco Mondelli 215 3 0 21 May 2025
Progressive Feedforward Collapse of ResNet Training Sicong Wang Kuo Gai Shihua Zhang AI4CE 231 8 0 02 May 2024
Towards Understanding Neural Collapse: The Effects of Batch Normalization and Weight Decay Leyan Pan Xinyuan Cao 300 6 0 09 Sep 2023
A Law of Data Separation in Deep LearningProceedings of the National Academy of Sciences of the United States of America (PNAS), 2022 Hangfeng He Weijie J. Su OOD 280 49 0 31 Oct 2022
Perturbation Analysis of Neural CollapseInternational Conference on Machine Learning (ICML), 2022 Tom Tirer Haoxiang Huang Jonathan Niles-Weed AAML 266 30 0 29 Oct 2022