Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability

26 July 2022

Papers citing "Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability"

37 / 37 papers shown

Title
Towards Quantifying the Hessian Structure of Neural Networks Zhaorui Dong Yushun Zhang Z. Luo Jianfeng Yao Ruoyu Sun 26 0 0 05 May 2025
Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes Ruiqi Zhang Jingfeng Wu Licong Lin Peter L. Bartlett 20 0 0 05 Apr 2025
A Minimalist Example of Edge-of-Stability and Progressive Sharpening Liming Liu Zixuan Zhang S. Du T. Zhao 74 0 0 04 Mar 2025
Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to Chaos Dayal Singh Kalra Tianyu He M. Barkeshli 47 4 0 17 Feb 2025
Simplicity Bias via Global Convergence of Sharpness Minimization Khashayar Gatmiry Zhiyuan Li Sashank J. Reddi Stefanie Jegelka 19 1 0 21 Oct 2024
Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization Yuhang Cai Jingfeng Wu Song Mei Michael Lindsey Peter L. Bartlett 32 2 0 12 Jun 2024
Training on the Edge of Stability Is Caused by Layerwise Jacobian Alignment Mark Lowell Catharine A. Kastner 20 0 0 31 May 2024
Deep linear networks for regression are implicitly regularized towards flat minima Pierre Marion Lénaic Chizat ODL 26 5 0 22 May 2024
Deconstructing the Goldilocks Zone of Neural Network Initialization Artem Vysogorets Anna Dawid Julia Kempe 35 1 0 05 Feb 2024
GD doesn't make the cut: Three ways that non-differentiability affects neural network training Siddharth Krishna Kumar AAML 18 2 0 16 Jan 2024
Gradient Descent with Polyak's Momentum Finds Flatter Minima via Large Catapults Prin Phunyaphibarn Junghyun Lee Bohan Wang Huishuai Zhang Chulhee Yun 16 0 0 25 Nov 2023
Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization Elan Rosenfeld Andrej Risteski 25 10 0 07 Nov 2023
Good regularity creates large learning rate implicit biases: edge of stability, balancing, and catapult Yuqing Wang Zhenghao Xu Tuo Zhao Molei Tao 24 10 0 26 Oct 2023
Irreducible Curriculum for Language Model Pretraining Simin Fan Martin Jaggi 22 9 0 23 Oct 2023
RSAM: Learning on manifolds with Riemannian Sharpness-aware Minimization Kenneth Allen Hoang-Phi Nguyen Tung Pham Ming-Jun Lai Mehrtash Harandi Dinh Q. Phung Trung Le AAML 19 2 0 29 Sep 2023
Learning Stochastic Dynamical Systems as an Implicit Regularization with Graph Neural Networks Jinqiu Guo Ting Gao Yufu Lan Peng Zhang Sikun Yang Jinqiao Duan 13 0 0 12 Jul 2023
Trajectory Alignment: Understanding the Edge of Stability Phenomenon via Bifurcation Theory Minhak Song Chulhee Yun 26 9 1 09 Jul 2023
The Inductive Bias of Flatness Regularization for Deep Matrix Factorization Khashayar Gatmiry Zhiyuan Li Ching-Yao Chuang Sashank J. Reddi Tengyu Ma Stefanie Jegelka ODL 17 11 0 22 Jun 2023
When and Why Momentum Accelerates SGD:An Empirical Study Jingwen Fu Bohan Wang Huishuai Zhang Zhizheng Zhang Wei Chen Na Zheng 12 10 0 15 Jun 2023
Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning Libin Zhu Chaoyue Liu Adityanarayanan Radhakrishnan M. Belkin 30 13 0 07 Jun 2023
SANE: The phases of gradient descent through Sharpness Adjusted Number of Effective parameters Lawrence Wang Stephen J. Roberts 17 0 0 29 May 2023
The Crucial Role of Normalization in Sharpness-Aware Minimization Yan Dai Kwangjun Ahn S. Sra 21 17 0 24 May 2023
On progressive sharpening, flat minima and generalisation L. MacDonald Jack Valmadre Simon Lucey 19 4 0 24 May 2023
Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond Itai Kreisler Mor Shpigel Nacson Daniel Soudry Y. Carmon 23 13 0 22 May 2023
Loss Spike in Training Neural Networks Zhongwang Zhang Z. Xu 28 4 0 20 May 2023
Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability Jingfeng Wu Vladimir Braverman Jason D. Lee 24 16 0 19 May 2023
Phase diagram of early training dynamics in deep neural networks: effect of the learning rate, depth, and width Dayal Singh Kalra M. Barkeshli 13 9 0 23 Feb 2023
Learning threshold neurons via the "edge of stability" Kwangjun Ahn Sébastien Bubeck Sinho Chewi Y. Lee Felipe Suarez Yi Zhang MLT 31 36 0 14 Dec 2022
Maximal Initial Learning Rates in Deep ReLU Networks Gaurav M. Iyer Boris Hanin David Rolnick 18 9 0 14 Dec 2022
Improving Multi-task Learning via Seeking Task-based Flat Regions Hoang Phan Lam C. Tran Ngoc N. Tran Nhat Ho Dinh Q. Phung Trung Le 17 10 0 24 Nov 2022
Second-order regression models exhibit progressive sharpening to the edge of stability Atish Agarwala Fabian Pedregosa Jeffrey Pennington 25 26 0 10 Oct 2022
Understanding Edge-of-Stability Training Dynamics with a Minimalist Example Xingyu Zhu Zixuan Wang Xiang Wang Mo Zhou Rong Ge 64 35 0 07 Oct 2022
Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability Alexandru Damian Eshaan Nichani Jason D. Lee 22 76 0 30 Sep 2022
A PDE-based Explanation of Extreme Numerical Sensitivities and Edge of Stability in Training Neural Networks Yuxin Sun Dong Lao G. Sundaramoorthi A. Yezzi 16 3 0 04 Jun 2022
Understanding Gradient Descent on Edge of Stability in Deep Learning Sanjeev Arora Zhiyuan Li A. Panigrahi MLT 75 88 0 19 May 2022
What Happens after SGD Reaches Zero Loss? --A Mathematical Framework Zhiyuan Li Tianhao Wang Sanjeev Arora MLT 83 98 0 13 Oct 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 156 233 0 04 Mar 2020