Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning

12 February 2024

Papers citing "Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning"

8 / 8 papers shown

Title
Geometric Inductive Biases of Deep Networks: The Role of Data and Architecture Sajad Movahedi Antonio Orvieto Seyed-Mohsen Moosavi-Dezfooli AAML AI4CE 47 0 0 15 Oct 2024
Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse Arthur Jacot Peter Súkeník Zihan Wang Marco Mondelli 26 1 0 07 Oct 2024
How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning Arthur Jacot Seok Hoan Choi Yuxiao Wen AI4CE 67 2 0 08 Jul 2024
Hamiltonian Mechanics of Feature Learning: Bottleneck Structure in Leaky ResNets Arthur Jacot Alexandre Kaiser 28 0 0 27 May 2024
Neural Collapse versus Low-rank Bias: Is Deep Neural Collapse Really Optimal? Peter Súkeník Marco Mondelli Christoph H. Lampert AI4CE 30 5 0 23 May 2024
Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions Arthur Jacot 34 24 0 29 Sep 2022
What Happens after SGD Reaches Zero Loss? --A Mathematical Framework Zhiyuan Li Tianhao Wang Sanjeev Arora MLT 83 98 0 13 Oct 2021
A General Theory of Equivariant CNNs on Homogeneous Spaces Taco S. Cohen Mario Geiger Maurice Weiler MLT AI4CE 146 289 0 05 Nov 2018