paper-with-me

Papers

Model Generalization: A Sharpness Aware Optimization Perspective

2022-08-14 · Jozef Marus Coldenhoff, Chengkun Li, Yurui Zhu

Sharpness-Aware Minimization (SAM) and adaptive sharpness-aware minimization (ASAM) aim to improve the model generalization. And in this project, we proposed three experiments to valid their generalization from the sharpness aware perspective. And our experiments show that sharpness aware-based optimization techniques could help to provide models with strong generalization ability. Our experiments also show that ASAM could improve the generalization performance on un-normalized data, but further research is needed to confirm this.

📄 PDF Abstract BibTeX arXiv:2208.06915

Code (1)

CharlieLeee/Sharpness-Aware-Generalization 공식 구현 pytorch

Tasks

modelvalid

Methods 이 논문이 사용한 방법론

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…
Sharpness-Aware Minimization Sharpness-Aware Minimization, or SAM, is a procedure that improves model generalization by simultaneously minimizing loss value and loss sharpness. SAM functions by…

Similar Papers 제목 키워드 기반

Gradient constrained sharpness-aware prompt learning for vision-language models

2023-09-14 · Liangchen Liu, Nannan Wang, Dawei Zhou, Xinbo Gao 외

This paper targets a novel trade-off problem in generalizable prompt learning for vision-language models (VLM), i.e., improving the performance on unseen classes while maintaining the performance on seen classes. Compari…

Prompt Learning

RSAM: Learning on manifolds with Riemannian Sharpness-aware Minimization

2023-09-29 · Tuan Truong, Hoang-Phi Nguyen, Tung Pham, Minh-Tuan Tran 외

Nowadays, understanding the geometry of the loss landscape shows promise in enhancing a model's generalization ability. In this work, we draw upon prior works that apply geometric principles to optimization and present a…

Contrastive Learningimage-classificationImage Classification

X-SAM: Boosting Sharpness-Aware Minimization with Dominant-Eigenvector Gradient Correction

2026-01-15 · Hongru Duan, Yongle Chen, Lei Guan arxiv

Sharpness-Aware Minimization (SAM) aims to improve generalization by minimizing a worst-case perturbed loss over a small neighborhood of model parameters. However, during training, its optimization behavior does not alwa…

1st-Order Magic: Analysis of Sharpness-Aware Minimization

2024-11-03 · Nalin Tiwary, Siddarth Aananth

Sharpness-Aware Minimization (SAM) is an optimization technique designed to improve generalization by favoring flatter loss minima. To achieve this, SAM optimizes a modified objective that penalizes sharpness, using comp…

COSCO: A Sharpness-Aware Training Framework for Few-shot Multivariate Time Series Classification

2024-09-15 · Jesus Barreda, Ashley Gomez, Ruben Puga, Kaixiong Zhou 외

Multivariate time series classification is an important task with widespread domains of applications. Recently, deep neural networks (DNN) have achieved state-of-the-art performance in time series classification. However…

ClassificationTime SeriesTime Series Classification