Hamiltonian Mechanics of Feature Learning: Bottleneck Structure in Leaky ResNets

27 May 2024

Papers citing "Hamiltonian Mechanics of Feature Learning: Bottleneck Structure in Leaky ResNets"

23 / 23 papers shown

Title
Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning Yuxiao Wen Arthur Jacot 90 7 0 12 Feb 2024
Residual Alignment: Uncovering the Mechanisms of Residual Networks Jianing Li Vardan Papyan AI4TS 27 5 0 17 Jan 2024
Mechanism of feature learning in convolutional neural networks Daniel Beaglehole Adityanarayanan Radhakrishnan Parthe Pandit Misha Belkin FAtt MLT 56 14 0 01 Sep 2023
Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff Arthur Jacot MLT 70 14 0 30 May 2023
A Rainbow in Deep Network Black Boxes Florentin Guth Brice Ménard G. Rochette S. Mallat 74 10 0 29 May 2023
$Implicit bias of SGD in $L_{2}$-regularized linear DNNs: One-way jumps from high to low rank$ Implicit bias of SGD in $L_{2}$ -regularized linear DNNs: One-way jumps from high to low rank Zihan Wang Arthur Jacot 52 19 0 25 May 2023
Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model Peter Súkeník Marco Mondelli Christoph H. Lampert 43 24 0 22 May 2023
Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions Arthur Jacot 58 26 0 29 Sep 2022
$Feature Learning in $L_{2}$-regularized DNNs: Attraction/Repulsion and Sparsity$ Feature Learning in $L_{2}$ -regularized DNNs: Attraction/Repulsion and Sparsity Arthur Jacot Eugene Golikov Clément Hongler Franck Gabriel MLT 56 17 0 31 May 2022
Turnpike in optimal control of PDEs, ResNets, and beyond Borjan Geshkovski Enrique Zuazua 32 33 0 08 Feb 2022
The staircase property: How hierarchical structure can guide deep learning Emmanuel Abbe Enric Boix-Adserà Matthew Brennan Guy Bresler Dheeraj M. Nagaraj 37 51 0 24 Aug 2021
Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning Zhiyuan Li Yuping Luo Kaifeng Lyu 49 125 0 17 Dec 2020
Prevalence of Neural Collapse during the terminal phase of deep learning training Vardan Papyan Xuemei Han D. Donoho 138 563 0 18 Aug 2020
Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss Lénaïc Chizat Francis R. Bach MLT 79 336 0 11 Feb 2020
Similarity of Neural Network Representations Revisited Simon Kornblith Mohammad Norouzi Honglak Lee Geoffrey E. Hinton 133 1,382 0 01 May 2019
Towards Understanding Linear Word Analogies Kawin Ethayarajh David Duvenaud Graeme Hirst 43 114 0 11 Oct 2018
Neural Ordinary Differential Equations T. Chen Yulia Rubanova J. Bettencourt David Duvenaud AI4CE 281 5,024 0 19 Jun 2018
Implicit Bias of Gradient Descent on Linear Convolutional Networks Suriya Gunasekar Jason D. Lee Daniel Soudry Nathan Srebro MDE 78 408 0 01 Jun 2018
Characterizing Implicit Bias in Terms of Optimization Geometry Suriya Gunasekar Jason D. Lee Daniel Soudry Nathan Srebro AI4CE 69 404 0 22 Feb 2018
Deep Learning and the Information Bottleneck Principle Naftali Tishby Noga Zaslavsky DRL 150 1,570 0 09 Mar 2015
Breaking the Curse of Dimensionality with Convex Neural Networks Francis R. Bach 145 703 0 30 Dec 2014
Visualizing and Understanding Convolutional Networks Matthew D. Zeiler Rob Fergus FAtt SSL 400 15,825 0 12 Nov 2013
Efficient Estimation of Word Representations in Vector Space Tomas Mikolov Kai Chen G. Corrado J. Dean 3DV 593 31,406 0 16 Jan 2013