{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/paths-and-ambient-spaces-in-neural-loss","title":"Paths and Ambient Spaces in Neural Loss Landscapes","arxiv_id":"2503.03382","date":"2025-03-05","proceeding":null,"authors":["Daniel Dold","Julius Kobialka","Nicolai Palm","Emanuel Sommer","David Rügamer","Oliver Dürr"],"abstract":"Understanding the structure of neural network loss surfaces, particularly the emergence of low-loss tunnels, is critical for advancing neural network theory and practice. In this paper, we propose a novel approach to directly embed loss tunnels into the loss landscape of neural networks. Exploring the properties of these loss tunnels offers new insights into their length and structure and sheds light on some common misconceptions. We then apply our approach to Bayesian neural networks, where we improve subspace inference by identifying pitfalls and proposing a more natural prior that better guides the sampling procedure.","url_abs":"https://arxiv.org/abs/2503.03382v1","url_pdf":"https://arxiv.org/pdf/2503.03382v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"paths-and-ambient-spaces-in-neural-loss","repo_url":"https://github.com/doldd/Paths-and-Ambient-Spaces","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null}],"tasks":[{"task_slug":"misconceptions","task_name":"Misconceptions"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}