Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff

30 May 2023

Papers citing "Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff"

8 / 8 papers shown

Title
How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning Arthur Jacot Seok Hoan Choi Yuxiao Wen AI4CE 86 2 0 08 Jul 2024
Hamiltonian Mechanics of Feature Learning: Bottleneck Structure in Leaky ResNets Arthur Jacot Alexandre Kaiser 31 0 0 27 May 2024
Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning Yuxiao Wen Arthur Jacot 45 6 0 12 Feb 2024
Layer-wise Linear Mode Connectivity Linara Adilova Maksym Andriushchenko Michael Kamp Asja Fischer Martin Jaggi FedML FAtt MoMe 26 15 0 13 Jul 2023
ReLU Neural Networks with Linear Layers are Biased Towards Single- and Multi-Index Models Suzanna Parkinson Greg Ongie Rebecca Willett 60 6 0 24 May 2023
Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions Arthur Jacot 34 24 0 29 Sep 2022
The Role of Linear Layers in Nonlinear Interpolating Networks Greg Ongie Rebecca Willett 54 15 0 02 Feb 2022
What Happens after SGD Reaches Zero Loss? --A Mathematical Framework Zhiyuan Li Tianhao Wang Sanjeev Arora MLT 83 98 0 13 Oct 2021