{"slug": "the-best-optimizer-depends-on-batch-size", "title": "The Best Optimizer Depends on Batch Size", "summary": "A paper submitted to arXiv on 6 Oct 2026 (arXiv:2610.08975) finds that the best optimizer for language model pretraining changes with batch size even after extensive hyperparameter tuning, and that no principled scaling rule for Muon works consistently across training settings. The authors challenge the common practice of benchmarking adaptive optimizers at a single batch size, arguing that hyperparameter scaling rules do not preserve optimizer rankings as batch size and gradient noise change.", "body_md": "# Computer Science > Machine Learning\n\n  [Submitted on 6 Oct 2026]\n\n# Title:The Best Optimizer Depends on Batch Size\n\n[View PDF](https://arxiv.org/pdf/2610.08975)\n\n[HTML (experimental)](https://arxiv.org/html/2610.08975v1)\n\nAbstract:A plethora of new adaptive optimizers are designed to efficiently estimate and use minibatch gradient statistics to shape parameter updates, but they are typically benchmarked at a single batch size. Hyperparameter scaling rules promise to preserve performance as batch size and gradient noise change, suggesting that the best optimizer at one batch size should remain the best at another. We challenge this approach to developing and evaluating optimizers by showing: (1) no principled scaling rule for Muon works consistently across training settings, and (2) the best optimizer for language model pretraining changes with batch size even after extensive hyperparameter tuning.\n    \n\n### Additional Features\n\n### Current browse context:\n\ncs.LG\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\nIArxiv Recommender\n\n*(*[What is IArxiv?](https://iarxiv.org/about))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth 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.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/the-best-optimizer-depends-on-batch-size", "canonical_source": "https://arxiv.org/abs/2610.08975", "published_at": "2026-10-08 04:00:00+00:00", "updated_at": "2026-10-08 04:19:08.628402+00:00", "lang": "en", "topics": ["machine-learning", "ai-research", "large-language-models", "artificial-intelligence"], "entities": ["arXiv", "Muon"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/the-best-optimizer-depends-on-batch-size", "markdown": "https://wpnews.pro/news/the-best-optimizer-depends-on-batch-size.md", "text": "https://wpnews.pro/news/the-best-optimizer-depends-on-batch-size.txt", "jsonld": "https://wpnews.pro/news/the-best-optimizer-depends-on-batch-size.jsonld"}}