{"slug": "deep-learning-is-not-so-mysterious-or-different", "title": "Deep Learning Is Not So Mysterious or Different", "summary": "A paper by Andrew Wilson and colleagues, submitted to arXiv on March 3, 2025, argues that deep learning's generalization behaviors, such as benign overfitting and double descent, are not unique to neural networks and can be explained by long-standing frameworks like PAC-Bayes and countable hypothesis bounds. The authors propose 'soft inductive biases' as a unifying principle, suggesting that flexible hypothesis spaces with a preference for simpler solutions can encode these behaviors across model classes, though they acknowledge deep learning's distinct strengths in representation learning and mode connectivity.", "body_md": "# Computer Science > Machine Learning\n\n[Submitted on 3 Mar 2025 (\n\n[v1](https://arxiv.org/abs/2503.02113v1)), last revised 10 Jul 2025 (this version, v2)]# Title:Deep Learning is Not So Mysterious or Different\n\n[View PDF](/pdf/2503.02113)\n\n[HTML (experimental)](https://arxiv.org/html/2503.02113v2)\n\nAbstract:Deep neural networks are often seen as different from other model classes by defying conventional notions of generalization. Popular examples of anomalous generalization behaviour include benign overfitting, double descent, and the success of overparametrization. We argue that these phenomena are not distinct to neural networks, or particularly mysterious. Moreover, this generalization behaviour can be intuitively understood, and rigorously characterized, using long-standing generalization frameworks such as PAC-Bayes and countable hypothesis bounds. We present soft inductive biases as a key unifying principle in explaining these phenomena: rather than restricting the hypothesis space to avoid overfitting, embrace a flexible hypothesis space, with a soft preference for simpler solutions that are consistent with the data. This principle can be encoded in many model classes, and thus deep learning is not as mysterious or different from other model classes as it might seem. However, we also highlight how deep learning is relatively distinct in other ways, such as its ability for representation learning, phenomena such as mode connectivity, and its relative universality.\n\n## Submission history\n\nFrom: Andrew Wilson [[view email](/show-email/57319f6c/2503.02113)]\n\n**Mon, 3 Mar 2025 22:56:04 UTC (1,206 KB)**\n\n[[v1]](/abs/2503.02113v1)**[v2]** Thu, 10 Jul 2025 13:56:52 UTC (1,231 KB)\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/))# 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))# 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))# 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/deep-learning-is-not-so-mysterious-or-different", "canonical_source": "https://arxiv.org/abs/2503.02113", "published_at": "2026-08-30 09:06:15+00:00", "updated_at": "2026-08-30 09:21:54.597240+00:00", "lang": "en", "topics": ["machine-learning", "artificial-intelligence"], "entities": ["Andrew Wilson", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/deep-learning-is-not-so-mysterious-or-different", "markdown": "https://wpnews.pro/news/deep-learning-is-not-so-mysterious-or-different.md", "text": "https://wpnews.pro/news/deep-learning-is-not-so-mysterious-or-different.txt", "jsonld": "https://wpnews.pro/news/deep-learning-is-not-so-mysterious-or-different.jsonld"}}