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

arXiv: https://arxiv.org/abs/2207.12678 · HTML: https://mlsanity.com/paper/2207.12678/

## Key facts

- Cited by 63 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 37 references that are in the map.
- First posted on arXiv 26 Jul 2022.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Neural Tangent Kernel: Convergence and Generalization in Neural Networks](https://mlsanity.com/paper/1806.07572/) (2018)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [Optimization Methods for Large-Scale Machine Learning](https://mlsanity.com/paper/1606.04838/) (2016)
- [Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent](https://mlsanity.com/paper/1902.06720/) (2019)
- [On Lazy Training in Differentiable Programming](https://mlsanity.com/paper/1812.07956/) (2018)
- [Gradient Descent Provably Optimizes Over-parameterized Neural Networks](https://mlsanity.com/paper/1810.02054/) (2018)
- [Gradient Descent Finds Global Minima of Deep Neural Networks](https://mlsanity.com/paper/1811.03804/) (2018)
- [Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks](https://mlsanity.com/paper/1901.08584/) (2019)
- [Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability](https://mlsanity.com/paper/2103.00065/) (2021)
- [Empirical Analysis of the Hessian of Over-Parametrized Neural Networks](https://mlsanity.com/paper/1706.04454/) (2017)
- [The large learning rate phase of deep learning: the catapult mechanism](https://mlsanity.com/paper/2003.02218/) (2020)
- [Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond](https://mlsanity.com/paper/1611.07476/) (2016)
- [The Break-Even Point on Optimization Trajectories of Deep Neural Networks](https://mlsanity.com/paper/2002.09572/) (2020)
- [Understanding Gradient Descent on Edge of Stability in Deep Learning](https://mlsanity.com/paper/2205.09745/) (2022)
- [Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks](https://mlsanity.com/paper/1909.12292/) (2019)
- [What Happens after SGD Reaches Zero Loss? --A Mathematical Framework](https://mlsanity.com/paper/2110.06914/) (2021)
- [Understanding the unstable convergence of gradient descent](https://mlsanity.com/paper/2204.01050/) (2022)
- [Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction](https://mlsanity.com/paper/2206.07085/) (2022)
- [A Walk with SGD](https://mlsanity.com/paper/1802.08770/) (2018)
- [Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians](https://mlsanity.com/paper/1901.08244/) (2019)
- [The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks](https://mlsanity.com/paper/2006.14599/) (2020)
- [Dissecting Hessian: Understanding Common Structure of Hessian in Neural Networks](https://mlsanity.com/paper/2010.04261/) (2020)
- [Pathological spectra of the Fisher information metric and its variants in deep neural networks](https://mlsanity.com/paper/1910.05992/) (2019)
- [The Normalization Method for Alleviating Pathological Sharpness in Wide Neural Networks](https://mlsanity.com/paper/1906.02926/) (2019)

## Built on by (most cited first, 30 of 63)

- [Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability](https://mlsanity.com/paper/2209.15594/) (2022)
- [Understanding Edge-of-Stability Training Dynamics with a Minimalist Example](https://mlsanity.com/paper/2210.03294/) (2022)
- [Learning threshold neurons via the "edge of stability"](https://mlsanity.com/paper/2212.07469/) (2022)
- [Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability](https://mlsanity.com/paper/2305.11788/) (2023)
- [Second-order regression models exhibit progressive sharpening to the edge of stability](https://mlsanity.com/paper/2210.04860/) (2022)
- [Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency](https://mlsanity.com/paper/2402.15926/) (2024)
- [Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning](https://mlsanity.com/paper/2306.04815/) (2023)
- [The Crucial Role of Normalization in Sharpness-Aware Minimization](https://mlsanity.com/paper/2305.15287/) (2023)
- [Trajectory Alignment: Understanding the Edge of Stability Phenomenon via Bifurcation Theory](https://mlsanity.com/paper/2307.04204/) (2023)
- [Good regularity creates large learning rate implicit biases: edge of stability, balancing, and catapult](https://mlsanity.com/paper/2310.17087/) (2023)
- [Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to Chaos](https://mlsanity.com/paper/2311.02076/) (2023)
- [Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot](https://mlsanity.com/paper/2406.06893/) (2024)
- [Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond](https://mlsanity.com/paper/2305.13064/) (2023)
- [Phase diagram of early training dynamics in deep neural networks: effect of the learning rate, depth, and width](https://mlsanity.com/paper/2302.12250/) (2023)
- [When and Why Momentum Accelerates SGD:An Empirical Study](https://mlsanity.com/paper/2306.09000/) (2023)
- [Deep linear networks for regression are implicitly regularized towards flat minima](https://mlsanity.com/paper/2405.13456/) (2024)
- [Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization](https://mlsanity.com/paper/2406.08654/) (2024)
- [Loss Spike in Training Neural Networks](https://mlsanity.com/paper/2305.12133/) (2023)
- [Irreducible Curriculum for Language Model Pretraining](https://mlsanity.com/paper/2310.15389/) (2023)
- [Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective](https://mlsanity.com/paper/2211.13723/) (2022)
- [Understanding Multi-phase Optimization Dynamics and Rich Nonlinear Behaviors of ReLU Networks](https://mlsanity.com/paper/2305.12467/) (2023)
- [Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization](https://mlsanity.com/paper/2311.04163/) (2023)
- [Towards Quantifying the Hessian Structure of Neural Networks](https://mlsanity.com/paper/2505.02809/) (2025)
- [Adaptive Preconditioners Trigger Loss Spikes in Adam](https://mlsanity.com/paper/2506.04805/) (2025)
- [Maximal Initial Learning Rates in Deep ReLU Networks](https://mlsanity.com/paper/2212.07295/) (2022)
- [Through the River: Understanding the Benefit of Schedule-Free Methods for Language Model Training](https://mlsanity.com/paper/2507.09846/) (2025)
- [On progressive sharpening, flat minima and generalisation](https://mlsanity.com/paper/2305.14683/) (2023)
- [Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes](https://mlsanity.com/paper/2504.04105/) (2025)
- [The Inductive Bias of Flatness Regularization for Deep Matrix Factorization](https://mlsanity.com/paper/2306.13239/) (2023)
- [Zeroth-Order Optimization Finds Flat Minima](https://mlsanity.com/paper/2506.05454/) (2025)

## Abstract (arXiv)

Recent findings (e.g., arXiv:2103.00065) demonstrate that modern neural networks trained by full-batch gradient descent typically enter a regime called Edge of Stability (EOS). In this regime, the sharpness, i.e., the maximum Hessian eigenvalue, first increases to the value 2/(step size) (the progressive sharpening phase) and then oscillates around this value (the EOS phase). This paper aims to analyze the GD dynamics and the sharpness along the optimization trajectory. Our analysis naturally divides the GD trajectory into four phases depending on the change of the sharpness. We empirically identify the norm of output layer weight as an interesting indicator of sharpness dynamics. Based on this empirical observation, we attempt to theoretically and empirically explain the dynamics of various key quantities that lead to the change of sharpness in each phase of EOS. Moreover, based on certain assumptions, we provide a theoretical proof of the sharpness behavior in EOS regime in two-layer fully-connected linear neural networks. We also discuss some other empirical findings and the limitation of our theoretical results.