EMASAM: a Computationally Efficient Sharpness-Aware Minimization via EMA-Guided Perturbations

[2608.15105] EMASAM: a Computationally Efficient Sharpness-Aware Minimization via EMA-Guided Perturbations Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2608.15105 (cs) [Submitted on 15 Aug 2026] Title: EMASAM: a Computationally Efficient Sharpness-Aware Minimization via EMA-Guided Perturbations Authors: Tanapat Ratchatorn , Masayuki Tanaka View a PDF of the paper titled EMASAM: a Computationally Efficient Sharpness-Aware Minimization via EMA-Guided Perturbations, by Tanapat Ratchatorn and 1 other authors View PDF HTML (experimental) Abstract: Recent progress in optimization research has highlighted the sharpness of the loss landscape as a key factor in narrowing the generalization gap. Motivated by this insight, Sharpness-Aware Minimization (SAM) was proposed as a training strategy that enhances generalization. Despite the promising performance, SAM suffers from its twice computational cost due to its core algorithm requiring an extra gradient computation during the perturbation step. To overcome this limitation, we introduce Exponential Moving Average Sharpness-Aware Minimization (EMASAM), a computationally efficient variant of SAM. EMASAM does not require the loss gradient in the perturbation step. Instead, EMASAM defines the perturbation direction based on the discrepancy between the main model and the EMA shadow model. This perturbation travels away from the stable average position toward the less stable area, acting as a softer yet cheaper alternative to SAM's worst-case scenario perturbation. Moreover, since EMASAM's perturbation does not rely on noisy mini-batch gradients, it mitigates the gradient-induced instability inherent in SAM. Hence, EMASAM eliminates the need for an extra backpropagation while also preserving the generalization ability of the SAM-style training. Several experiments have been performed and confirm the efficiency and robustness of our method. Comments: Accepted in ICPR2026. The project page can be accessed at this https URL Subjects: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2608.15105 [cs.LG] (or arXiv:2608.15105v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2608.15105 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Tanapat Ratchatorn [ view email ] [v1] Sat, 15 Aug 2026 08:10:31 UTC (617 KB) Full-text links: Access Paper: View a PDF of the paper titled EMASAM: a Computationally Efficient Sharpness-Aware Minimization via EMA-Guided Perturbations, by Tanapat Ratchatorn and 1 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2026-08 Change to browse by: cs cs.CV References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• EMASAM: a Computationally Efficient Sharpness-Aware Minimization via EMA-Guided Perturbations#611055
• The inverse elasto-acoustic problem#669029
• Retinex-based low-light image enhancement with multi-channel feature optimization.#150153
• Iterative Bayesian denoising based on variance stabilization using Contourlet Transform with Sharp Frequency Localization: application to EFTEM images#320278
• MixFrag: Fragility-Guided Mixed-Precision Post-Training Quantization for Vision Transformers#414087