Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models

• URL: http://arxiv.org/abs/2210.05497v1
• Date: Tue, 11 Oct 2022 14:53:58 GMT
• Title: Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models
• Authors: Qihuang Zhong, Liang Ding, Li Shen, Peng Mi, Juhua Liu, Bo Du and Dacheng Tao
• Abstract summary: Fine-tuning large pretrained language models on a limited training corpus usually suffers from poor computation. We propose a novel optimization procedure, namely FSAM, which introduces a Fisher mask to improve the efficiency and performance of SAM. We show that FSAM consistently outperforms the vanilla SAM by 0.671.98 average score among four different pretrained models.
• Score: 93.85178920914721
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fine-tuning large pretrained language models on a limited training corpus usually suffers from poor generalization. Prior works show that the recently-proposed sharpness-aware minimization (SAM) optimization method can improve the model generalization. However, SAM adds a perturbation to each model parameter equally (but not all parameters contribute equally to the optimization of training), which we argue is sub-optimal and will lead to excessive computation. In this paper, we propose a novel optimization procedure, namely FSAM, which introduces a Fisher mask to improve the efficiency and performance of SAM. In short, instead of adding perturbation to all parameters, FSAM uses the Fisher information to identity the important parameters and formulates a Fisher mask to obtain the sparse perturbation, i.e., making the optimizer focus on these important parameters. Experiments on various tasks in GLUE and SuperGLUE benchmarks show that FSAM consistently outperforms the vanilla SAM by 0.67~1.98 average score among four different pretrained models. We also empirically show that FSAM works well in other complex scenarios, e.g., fine-tuning on generation tasks or limited training data. Encouragingly, when training data is limited, FSAM improves the SAM by a large margin, i.e., up to 15.1.

Related papers

• Improving SAM Requires Rethinking its Optimization Formulation [57.601718870423454]
  Sharpness-Aware Minimization (SAM) is originally formulated as a zero-sum game where the weights of a network and a bounded perturbation try to minimize/maximize, respectively, the same differentiable loss. We argue that SAM should instead be reformulated using the 0-1 loss. As a continuous relaxation, we follow the simple conventional approach where the minimizing (maximizing) player uses an upper bound (lower bound) surrogate to the 0-1 loss. This leads to a novel formulation of SAM as a bilevel optimization problem, dubbed as BiSAM.
  arXiv  Detail & Related papers  (2024-07-17T20:22:33Z)
• Asymptotic Unbiased Sample Sampling to Speed Up Sharpness-Aware Minimization [17.670203551488218]
  We propose Asymptotic Unbiased Sampling to accelerate Sharpness-Aware Minimization (AUSAM) AUSAM maintains the model's generalization capacity while significantly enhancing computational efficiency. As a plug-and-play, architecture-agnostic method, our approach consistently accelerates SAM across a range of tasks and networks.
  arXiv  Detail & Related papers  (2024-06-12T08:47:44Z)
• Systematic Investigation of Sparse Perturbed Sharpness-Aware Minimization Optimizer [158.2634766682187]
  Deep neural networks often suffer from poor generalization due to complex and non- unstructured loss landscapes. SharpnessAware Minimization (SAM) is a popular solution that smooths the loss by minimizing the change of landscape when adding a perturbation. In this paper, we propose Sparse SAM (SSAM), an efficient and effective training scheme that achieves perturbation by a binary mask.
  arXiv  Detail & Related papers  (2023-06-30T09:33:41Z)
• Improved Deep Neural Network Generalization Using m-Sharpness-Aware Minimization [14.40189851070842]
  Sharpness-Aware Minimization (SAM) modifies the underlying loss function to guide descent methods towards flatter minima. Recent work suggests that mSAM can outperform SAM in terms of test accuracy. This paper presents a comprehensive empirical evaluation of mSAM on various tasks and datasets.
  arXiv  Detail & Related papers  (2022-12-07T00:37:55Z)
• Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach [132.37966970098645]
  One of the popular solutions is Sharpness-Aware Minimization (SAM), which minimizes the change of weight loss when adding a perturbation. In this paper, we propose an efficient effective training scheme coined as Sparse SAM (SSAM), which achieves double overhead of common perturbations. In addition, we theoretically prove that S can converge at the same SAM, i.e., $O(log T/sqrtTTTTTTTTTTTTTTTTT
  arXiv  Detail & Related papers  (2022-10-11T06:30:10Z)
• Towards Efficient and Scalable Sharpness-Aware Minimization [81.22779501753695]
  We propose a novel algorithm LookSAM that only periodically calculates the inner gradient ascent. LookSAM achieves similar accuracy gains to SAM while being tremendously faster. We are the first to successfully scale up the batch size when training Vision Transformers (ViTs)
  arXiv  Detail & Related papers  (2022-03-05T11:53:37Z)
• Efficient Sharpness-aware Minimization for Improved Training of Neural Networks [146.2011175973769]
  This paper proposes Efficient Sharpness Aware Minimizer (M) which boosts SAM s efficiency at no cost to its generalization performance. M includes two novel and efficient training strategies-StochasticWeight Perturbation and Sharpness-Sensitive Data Selection. We show, via extensive experiments on the CIFAR and ImageNet datasets, that ESAM enhances the efficiency over SAM from requiring 100% extra computations to 40% vis-a-vis bases.
  arXiv  Detail & Related papers  (2021-10-07T02:20:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.