$Feature Learning in $L_{2}$-regularized DNNs: Attraction/Repulsion and Sparsity$

Feature Learning in $L_{2}$ -regularized DNNs: Attraction/Repulsion and Sparsity

31 May 2022

Clément Hongler

Papers citing "Feature Learning in $L_{2}$-regularized DNNs: Attraction/Repulsion and Sparsity"

8 / 8 papers shown

Title
Geometry of Learning -- L2 Phase Transitions in Deep and Shallow Neural Networks Ibrahim Talha Ersoy Karoline Wiesner 25 0 0 10 May 2025
On the Cone Effect in the Learning Dynamics Zhanpeng Zhou Yongyi Yang Jie Ren Mahito Sugiyama Junchi Yan 53 0 0 20 Mar 2025
Hamiltonian Mechanics of Feature Learning: Bottleneck Structure in Leaky ResNets Arthur Jacot Alexandre Kaiser 38 0 0 27 May 2024
Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff Arthur Jacot MLT 26 13 0 30 May 2023
On the Stepwise Nature of Self-Supervised Learning James B. Simon Maksis Knutins Liu Ziyin Daniel Geisz Abraham J. Fetterman Joshua Albrecht SSL 39 30 0 27 Mar 2023
Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions Arthur Jacot 46 25 0 29 Sep 2022
The Role of Linear Layers in Nonlinear Interpolating Networks Greg Ongie Rebecca Willett 66 15 0 02 Feb 2022
The large learning rate phase of deep learning: the catapult mechanism Aitor Lewkowycz Yasaman Bahri Ethan Dyer Jascha Narain Sohl-Dickstein Guy Gur-Ari ODL 159 236 0 04 Mar 2020