sharpness-aware-minimization

Tag

Cards List
#sharpness-aware-minimization

From Perturbation Correction to Geometry-Aware Sampling: Sharpness-Guided Equilibrium Sampling for Balanced Flat Minima in Long-Tailed Learning

arXiv cs.LG · 2026-07-27 Cached

Introduces Sharpness-Guided Equilibrium Sampling (SGS) that dynamically adjusts sampling probabilities using sharpness estimates to achieve balanced flat minima in long-tailed learning, achieving significant gains on CIFAR-100 LT and ImageNet-LT.

0 favorites 0 likes
#sharpness-aware-minimization

Gradient-Energy Guided Block-Wise Perturbations for Sharpness-Aware Minimization

arXiv cs.LG · 2026-07-22 Cached

The paper proposes GEAR-SAM, which adaptively allocates the perturbation budget across network blocks using an exponential moving average of squared gradients, improving generalization without additional computational overhead.

0 favorites 0 likes
#sharpness-aware-minimization

Leveraging Extragradient for Effective Sharpness-Aware Minimization in Deep Learning

arXiv cs.LG · 2026-07-08 Cached

Proposes EISAM, a new optimizer that extends Sharpness-Aware Minimization using an extragradient step to find flatter minima, improving generalization and robustness while reducing sensitivity to hyperparameters. Outperforms SGD, Adam, and SAM on benchmarks.

0 favorites 0 likes
#sharpness-aware-minimization

Are Flat Minima an Illusion?

arXiv cs.LG · 2026-05-08 Cached

This paper challenges the common belief that flat minima cause better generalization in neural networks, arguing that 'weakness'—a reparameterization-invariant measure of function simplicity—is the true driver. Empirical results on MNIST and Fashion-MNIST show that weakness predicts generalization while sharpness anticorrelates, and the large-batch generalization advantage vanishes as training data increases.

0 favorites 0 likes
← Back to home

Submit Feedback