Enhancing Sharpness-Aware Optimization Through Variance Suppression
Sharpness-aware minimization (SAM) has well documented merits in enhancing generalization of deep neural networks, even without sizable data augmentation. Embracing the geometry of the loss function, where neighborhoods of 'flat minima' heighten generalization ability, SAM seeks 'flat valleys' by minimizing the maximum loss caused by an adversary perturbing parameters within the neighborhood. Although critical to account for sharpness of the loss function, such an 'over-friendly adversary' can curtail the outmost level of generalization. The novel approach of this contribution fosters stabilization of adversaries through variance suppression (VaSSO) to avoid such friendliness. VaSSO's provable stability safeguards its numerical improvement over SAM in model-agnostic tasks, including image classification and machine translation. In addition, experiments confirm that VaSSO endows SAM with robustness against high levels of label noise.
Code (1)
Tasks
Data Augmentationimage-classificationImage ClassificationMachine TranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
VASSO: Variance Suppression for Sharpness-Aware Minimization
Sharpness-aware minimization (SAM) has well-documented merits in enhancing generalization of deep neural network models. Accounting for sharpness in the loss function geometry, where neighborhoods of `flat minima' height…
A Universal Class of Sharpness-Aware Minimization Algorithms
Recently, there has been a surge in interest in developing optimization algorithms for overparameterized models as achieving generalization is believed to require algorithms with suitable biases. This interest centers on…
SharpZO: Hybrid Sharpness-Aware Vision Language Model Prompt Tuning via Forward-Only Passes
Fine-tuning vision language models (VLMs) has achieved remarkable performance across various downstream tasks; yet, it requires access to model gradients through backpropagation (BP), making them unsuitable for memory-co…
Language ModelingLanguage ModellingRSAM: Learning on manifolds with Riemannian Sharpness-aware Minimization
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 ClassificationDiM: $f$-Divergence Minimization Guided Sharpness-Aware Optimization for Semi-supervised Medical Image Segmentation
As a technique to alleviate the pressure of data annotation, semi-supervised learning (SSL) has attracted widespread attention. In the specific domain of medical image segmentation, semi-supervised methods (SSMIS) have b…
Image SegmentationMedical Image SegmentationSemantic SegmentationSemi-supervised Medical Image Segmentation