arXiv Machine Learning June 8, 2026 By Maria Matveev, Vit Fojtik, Hung-Hsu Chou, Gitta Kutyniok, Johannes Maly

Conflicting Biases at the Edge of Stability: Norm versus Sharpness Regularization

Read the original on arXiv Machine Learning →

arXiv:2505. 21423v3 Announce Type: replace Abstract: The remarkable generalization properties of overparameterized networks are often attributed to implicit biases, such as norm minimization at small learning rates and low sharpness in the Edge-of-Stability regime.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

safety

arXiv Machine Learning

Jul 14

Training Diagonal Linear Networks with Stochastic Sharpness-Aware Minimization

arXiv:2503. 11891v2 Announce Type: replace Abstract: We analyze the landscape and training dynamics of diagonal linear networks in a linear regression task, with the network parameters being perturbed by isotropic normal noise during training.

By Gabriel Clara, Sophie Langer, Johannes Schmidt-Hieber

arXiv Machine Learning

Jun 18

How Does the ReLU Activation Affect the Implicit Bias of Gradient Descent on High-dimensional Neural Network Regression?

arXiv:2603. 04895v2 Announce Type: replace-cross Abstract: Overparameterized ML models, including neural networks, typically induce underdetermined training objectives with multiple global minima.

By Kuo-Wei Lai, Guanghui Wang, Molei Tao, Vidya Muthukumar

safety

arXiv Machine Learning

Aug 11

Error Bound Analysis for the Regularized Loss of Deep Linear Neural Networks

arXiv:2502. 11152v4 Announce Type: replace-cross Abstract: The optimization foundations of deep linear networks have recently received significant attention.

By Po Chen, Rujun Jiang, Peng Wang

arXiv Machine Learning

Jul 15

Gradient Flow Dynamics and Implicit Bias of Diagonal Linear Networks under Infinitesimal Initialization

arXiv:2607. 12332v1 Announce Type: new Abstract: We study the gradient flow dynamics of diagonal linear networks for regression tasks under infinitesimal initialization.

By Jiajie Zhao, Jianxing Wang, Junjie Yang, Zhiwei Bai, Yaoyu Zhang

safety

arXiv AI

Jun 2

Stability Analysis of Sharpness-Aware Minimization

arXiv:2301. 06308v2 Announce Type: replace-cross Abstract: Sharpness-aware minimization (SAM) is a training method that seeks to find flat minima in deep learning, resulting in state-of-the-art performance across various domains.

By Hoki Kim, Jinseong Park, Yujin Choi, Jaewook Lee

diffusion benchmarks

arXiv Machine Learning

Jul 17

To Grok Grokking: Provable Grokking in Ridge Regression

arXiv:2601. 19791v4 Announce Type: replace Abstract: We study grokking, the onset of generalization long after overfitting, in a classical ridge regression setting.

By Mingyue Xu, Gal Vardi, Itay Safran

Related stories

Training Diagonal Linear Networks with Stochastic Sharpness-Aware Minimization

How Does the ReLU Activation Affect the Implicit Bias of Gradient Descent on High-dimensional Neural Network Regression?

Error Bound Analysis for the Regularized Loss of Deep Linear Neural Networks

Gradient Flow Dynamics and Implicit Bias of Diagonal Linear Networks under Infinitesimal Initialization

Stability Analysis of Sharpness-Aware Minimization

To Grok Grokking: Provable Grokking in Ridge Regression