SAMPa: Sharpness-aware Minimization Parallelized

• URL: http://arxiv.org/abs/2410.10683v1
• Date: Mon, 14 Oct 2024 16:21:23 GMT
• Title: SAMPa: Sharpness-aware Minimization Parallelized
• Authors: Wanyun Xie, Thomas Pethick, Volkan Cevher,
• Abstract summary: Sharpness-aware (SAM) has been shown to improve the generalization of neural networks. Each SAM update requires emphsequentially computing two gradients, effectively doubling the per-iteration cost. We propose a simple modification of SAM, termed SAMPa, which allows us to fully parallelize the two gradient computations.
• Score: 51.668052890249726
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sharpness-aware minimization (SAM) has been shown to improve the generalization of neural networks. However, each SAM update requires \emph{sequentially} computing two gradients, effectively doubling the per-iteration cost compared to base optimizers like SGD. We propose a simple modification of SAM, termed SAMPa, which allows us to fully parallelize the two gradient computations. SAMPa achieves a twofold speedup of SAM under the assumption that communication costs between devices are negligible. Empirical results show that SAMPa ranks among the most efficient variants of SAM in terms of computational time. Additionally, our method consistently outperforms SAM across both vision and language tasks. Notably, SAMPa theoretically maintains convergence guarantees even for \emph{fixed} perturbation sizes, which is established through a novel Lyapunov function. We in fact arrive at SAMPa by treating this convergence guarantee as a hard requirement -- an approach we believe is promising for developing SAM-based methods in general. Our code is available at \url{https://github.com/LIONS-EPFL/SAMPa}.

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)
• An Adaptive Policy to Employ Sharpness-Aware Minimization [5.5347134457499845]
  Sharpness-aware minimization (SAM) searches for flat minima by min-max optimization. Recent state-of-the-arts reduce the fraction of SAM updates. Two efficient algorithms, AE-SAM and AE-LookSAM, are proposed.
  arXiv  Detail & Related papers  (2023-04-28T06:23:32Z)
• K-SAM: Sharpness-Aware Minimization at the Speed of SGD [83.78737278889837]
  Sharpness-Aware Minimization (SAM) has emerged as a robust technique for improving the accuracy of deep neural networks. SAM incurs a high computational cost in practice, requiring up to twice as much computation as vanilla SGD. We propose to compute gradients in both stages of SAM on only the top-k samples with highest loss.
  arXiv  Detail & Related papers  (2022-10-23T21:49:58Z)
• 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)

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.