The Surprising Simplicity of the Early-Time Learning Dynamics of Neural
Networks

The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks

25 June 2020

Jeffrey Pennington

Papers citing "The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks"

18 / 18 papers shown

Title
How Do Large Language Models Acquire Factual Knowledge During Pretraining? Hoyeon Chang Jinho Park Seonghyeon Ye Sohee Yang Youngkyung Seo Du-Seong Chang Minjoon Seo KELM 37 32 0 17 Jun 2024
Hypernetwork-based Meta-Learning for Low-Rank Physics-Informed Neural Networks Woojin Cho Kookjin Lee Donsub Rim Noseong Park AI4CE PINN 34 16 0 14 Oct 2023
Robust Sparse Mean Estimation via Incremental Learning Jianhao Ma Ruidi Chen Yinghui He S. Fattahi Wei Hu 36 0 0 24 May 2023
Understanding the Initial Condensation of Convolutional Neural Networks Zhangchen Zhou Hanxu Zhou Yuqing Li Zhi-Qin John Xu MLT AI4CE 23 5 0 17 May 2023
Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics Nihal Murali A. Puli Ke Yu Rajesh Ranganath Kayhan Batmanghelich AAML 40 8 0 18 Feb 2023
Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing Jikai Jin Zhiyuan Li Kaifeng Lyu S. Du Jason D. Lee MLT 51 34 0 27 Jan 2023
When Expressivity Meets Trainability: Fewer than $n$ Neurons Can Work Jiawei Zhang Yushun Zhang Mingyi Hong Ruoyu Sun Zhi-Quan Luo 26 10 0 21 Oct 2022
On the Activation Function Dependence of the Spectral Bias of Neural Networks Q. Hong Jonathan W. Siegel Qinyan Tan Jinchao Xu 34 22 0 09 Aug 2022
Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability Z. Li Zixuan Wang Jian Li 19 42 0 26 Jul 2022
Neural Collapse: A Review on Modelling Principles and Generalization Vignesh Kothapalli 21 71 0 08 Jun 2022
Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials Eshaan Nichani Yunzhi Bai Jason D. Lee 27 10 0 08 Jun 2022
Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks Noam Razin Asaf Maman Nadav Cohen 46 29 0 27 Jan 2022
Overview frequency principle/spectral bias in deep learning Z. Xu Yaoyu Zhang Tao Luo FaML 30 65 0 19 Jan 2022
Deep Learning Through the Lens of Example Difficulty R. Baldock Hartmut Maennel Behnam Neyshabur 47 155 0 17 Jun 2021
FEAR: A Simple Lightweight Method to Rank Architectures Debadeepta Dey Shital C. Shah Sébastien Bubeck OOD 22 4 0 07 Jun 2021
RATT: Leveraging Unlabeled Data to Guarantee Generalization Saurabh Garg Sivaraman Balakrishnan J. Zico Kolter Zachary Chase Lipton 28 30 0 01 May 2021
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 159 234 0 04 Mar 2020
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks Lechao Xiao Yasaman Bahri Jascha Narain Sohl-Dickstein S. Schoenholz Jeffrey Pennington 224 348 0 14 Jun 2018