← Back to all news
arXiv Machine Learning By Jiaxin Deng, Junbiao Pang, Baochang Zhang, Qingming Huang

Bilateral Sharpness-Aware Minimization for Flatter Minima

Read the original on arXiv Machine Learning →

The paper introduces Bilateral Sharpness-Aware Minimization (BSAM), a new optimization method that combines the traditional Max-Sharpness (MaxS) metric with a newly defined Min-Sharpness (MinS) metric. By using the difference between the training loss and the minimum loss in a neighborhood around the current weights, BSAM creates a more comprehensive Flatness Indicator (FI) that guides the search toward flatter minima. Experiments show that BSAM improves generalization and robustness over vanilla SAM in tasks such as classification, transfer learning, human pose estimation, and network quantization.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Oct 9

Do Flatter Minima Drive Better Generalization? An Algorithmic Separation in Grokking

The paper investigates whether flatter loss landscapes drive better generalization in the context of Grokking. It shows that sharpness‑aware minimization (SAM) alone does not reliably induce the transition to generalization, but when combined with weight decay, SAM can accelerate this transition up to four times faster. The authors provide a theoretical analysis using a minimal two‑layer ReLU model, demonstrating that flatness alone cannot distinguish memorizing from generalizing solutions, while weight decay favors generalization and a local stability window explains SAM’s effect.

By Mohnish Harwani
More like this →