# SAM operates far from home: eigenvalue regularization as a dynamical phenomenon

arXiv: https://arxiv.org/abs/2302.08692 · HTML: https://mlsanity.com/paper/2302.08692/

## Key facts

- Cited by 24 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 17 Feb 2023.

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

- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [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)
- [On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima](https://mlsanity.com/paper/1609.04836/) (2016)
- [Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent](https://mlsanity.com/paper/1902.06720/) (2019)
- [Exploring Generalization in Deep Learning](https://mlsanity.com/paper/1706.08947/) (2017)
- [Sharp Minima Can Generalize For Deep Nets](https://mlsanity.com/paper/1703.04933/) (2017)
- [Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability](https://mlsanity.com/paper/2103.00065/) (2021)
- [Entropy-SGD: Biasing Gradient Descent Into Wide Valleys](https://mlsanity.com/paper/1611.01838/) (2016)
- [An Investigation into Neural Net Optimization via Hessian Eigenvalue Density](https://mlsanity.com/paper/1901.10159/) (2019)
- [The large learning rate phase of deep learning: the catapult mechanism](https://mlsanity.com/paper/2003.02218/) (2020)
- [Surrogate Gap Minimization Improves Sharpness-Aware Training](https://mlsanity.com/paper/2203.08065/) (2022)
- [Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability](https://mlsanity.com/paper/2209.15594/) (2022)
- [The Break-Even Point on Optimization Trajectories of Deep Neural Networks](https://mlsanity.com/paper/2002.09572/) (2020)
- [Towards Understanding Sharpness-Aware Minimization](https://mlsanity.com/paper/2206.06232/) (2022)
- [Sharpness-Aware Minimization Improves Language Model Generalization](https://mlsanity.com/paper/2110.08529/) (2021)
- [Adaptive Gradient Methods at the Edge of Stability](https://mlsanity.com/paper/2207.14484/) (2022)
- [How Does Sharpness-Aware Minimization Minimize Sharpness?](https://mlsanity.com/paper/2211.05729/) (2022)
- [The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima](https://mlsanity.com/paper/2210.01513/) (2022)
- [Second-order regression models exhibit progressive sharpening to the edge of stability](https://mlsanity.com/paper/2210.04860/) (2022)
- [SGD in the Large: Average-case Analysis, Asymptotics, and Stepsize Criticality](https://mlsanity.com/paper/2102.04396/) (2021)
- [Temperature check: theory and practice for training models with softmax-cross-entropy losses](https://mlsanity.com/paper/2010.07344/) (2020)
- [Homogenization of SGD in high-dimensions: Exact dynamics and generalization properties](https://mlsanity.com/paper/2205.07069/) (2022)
- [Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions](https://mlsanity.com/paper/2206.07252/) (2022)
- [Trajectory of Mini-Batch Momentum: Batch Size Saturation and Convergence in High Dimensions](https://mlsanity.com/paper/2206.01029/) (2022)

## Built on by (most cited first, 24 of 24)

- [Does SGD really happen in tiny subspaces?](https://mlsanity.com/paper/2405.16002/) (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)
- [Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late in Training](https://mlsanity.com/paper/2410.10373/) (2024)
- [Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima](https://mlsanity.com/paper/2306.09850/) (2023)
- [High dimensional analysis reveals conservative sharpening and a stochastic edge of stability](https://mlsanity.com/paper/2404.19261/) (2024)
- [Sharpness-Aware Minimization and the Edge of Stability](https://mlsanity.com/paper/2309.12488/) (2023)
- [From Stability to Chaos: Analyzing Gradient Descent Dynamics in Quadratic Regression](https://mlsanity.com/paper/2310.01687/) (2023)
- [Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning](https://mlsanity.com/paper/2504.14662/) (2025)
- [Noise Stability Optimization for Finding Flat Minima: A Hessian-based Regularization Approach](https://mlsanity.com/paper/2306.08553/) (2023)
- [A Universal Class of Sharpness-Aware Minimization Algorithms](https://mlsanity.com/paper/2406.03682/) (2024)
- [Neglected Hessian component explains mysteries in Sharpness regularization](https://mlsanity.com/paper/2401.10809/) (2024)
- [mSAM: Micro-Batch-Averaged Sharpness-Aware Minimization](https://mlsanity.com/paper/2302.09693/) (2023)
- [Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems](https://mlsanity.com/paper/2410.14802/) (2024)
- [On Statistical Properties of Sharpness-Aware Minimization: Provable Guarantees](https://mlsanity.com/paper/2302.11836/) (2023)
- [Flat Minima and Generalization: Insights from Stochastic Convex Optimization](https://mlsanity.com/paper/2511.03548/) (2025)
- [SASSHA: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian Approximation](https://mlsanity.com/paper/2502.18153/) (2025)
- [A Precise Characterization of SGD Stability Using Loss Surface Geometry](https://mlsanity.com/paper/2401.12332/) (2024)
- [Variational Learning Finds Flatter Solutions at the Edge of Stability](https://mlsanity.com/paper/2506.12903/) (2025)
- [Unveiling m-Sharpness Through the Structure of Stochastic Gradient Noise](https://mlsanity.com/paper/2509.18001/) (2025)
- [Characterizing Optimizer-Dependent Training Dynamics Through Hessian Eigenvector Displacement and Localization](https://mlsanity.com/paper/2606.30226/) (2026)
- [Convergence of optimizers implies eigenvalues filtering at equilibrium](https://mlsanity.com/paper/2510.09034/) (2025)
- [Why Some Models Resist Unlearning: A Linear Stability Perspective](https://mlsanity.com/paper/2602.02986/) (2026)
- [Explaining f-Divergence-Based Regularization via Local Curvature and Sharpness-Aware Minimization](https://mlsanity.com/paper/2609.09367/) (2026)

## Abstract (arXiv)

The Sharpness Aware Minimization (SAM) optimization algorithm has been shown to control large eigenvalues of the loss Hessian and provide generalization benefits in a variety of settings. The original motivation for SAM was a modified loss function which penalized sharp minima; subsequent analyses have also focused on the behavior near minima. However, our work reveals that SAM provides a strong regularization of the eigenvalues throughout the learning trajectory. We show that in a simplified setting, SAM dynamically induces a stabilization related to the edge of stability (EOS) phenomenon observed in large learning rate gradient descent. Our theory predicts the largest eigenvalue as a function of the learning rate and SAM radius parameters. Finally, we show that practical models can also exhibit this EOS stabilization, and that understanding SAM must account for these dynamics far away from any minima.