paper-with-me

Papers

Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems

2024-10-18 · Bingcong Li, Liang Zhang, Niao He

Sharpness-aware minimization (SAM) improves generalization of various deep learning tasks. Motivated by popular architectures such as LoRA, we explore the implicit regularization of SAM for scale-invariant problems involving two groups of variables. Instead of focusing on commonly used sharpness, this work introduces a concept termed balancedness, defined as the difference between the squared norm of two variables. This allows us to depict richer global behaviors of SAM. In particular, our theoretical and empirical findings reveal that i) SAM promotes balancedness; and ii) the regularization on balancedness is data-responsive -- outliers have stronger impact. The latter coincides with empirical observations that SAM outperforms SGD in the presence of outliers. Leveraging the implicit regularization, we develop a resource-efficient SAM variant, balancedness-aware regularization (BAR), tailored for scale-invariant problems such as finetuning language models with LoRA. BAR saves 95% computational overhead of SAM, with enhanced test performance across various tasks on RoBERTa, GPT2, and OPT-1.3B.

📄 PDF Abstract BibTeX arXiv:2410.14802

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Adam 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

Similar Papers 제목 키워드 기반

Unpacking the Implicit Norm Dynamics of Sharpness-Aware Minimization in Tensorized Models

2025-08-14 · Tianxiao Cao, Kyohei Atarashi, Hisashi Kashima arxiv

Sharpness-Aware Minimization (SAM) has been proven to be an effective optimization technique for improving generalization in overparameterized models. While prior works have explored the implicit regularization of SAM in…

parameter-efficient fine-tuningModel Compression

Sharpness-Aware Minimization with Adaptive Regularization for Training Deep Neural Networks

2024-12-22 · Jinping Zou, Xiaoge Deng, Tao Sun

Sharpness-Aware Minimization (SAM) has proven highly effective in improving model generalization in machine learning tasks. However, SAM employs a fixed hyperparameter associated with the regularization to characterize t…

Sharpness-Aware Minimization Revisited: Weighted Sharpness as a Regularization Term

2023-05-25 · Yun Yue, Jiadi Jiang, Zhiling Ye, Ning Gao 외

Deep Neural Networks (DNNs) generalization is known to be closely related to the flatness of minima, leading to the development of Sharpness-Aware Minimization (SAM) for seeking flatter minima and better generalization. …

Avoiding spurious sharpness minimization broadens applicability of SAM

2025-02-04 · Sidak Pal Singh, Hossein Mobahi, Atish Agarwala, Yann Dauphin

Curvature regularization techniques like Sharpness Aware Minimization (SAM) have shown great promise in improving generalization on vision tasks. However, we find that SAM performs poorly in domains like natural language…

Unveiling m-Sharpness Through the Structure of Stochastic Gradient Noise

2025-09-22 · Haocheng Luo, Mehrtash Harandi, Dinh Phung, Trung Le arxiv

Sharpness-aware minimization (SAM) has emerged as a highly effective technique to improve model generalization, but its underlying principles are not fully understood. We investigate m-sharpness, where SAM performance im…