{"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/the-full-spectrum-of-deep-net-hessians-at","title":"The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size","arxiv_id":"1811.07062","date":"2018-11-16","proceeding":null,"authors":["Vardan Papyan"],"abstract":"We apply state-of-the-art tools in modern high-dimensional numerical linear algebra to approximate efficiently the spectrum of the Hessian of modern deepnets, with tens of millions of parameters, trained on real data. Our results corroborate previous findings, based on small-scale networks, that the Hessian exhibits \"spiked\" behavior, with several outliers isolated from a continuous bulk. We decompose the Hessian into different components and study the dynamics with training and sample size of each term individually.","url_abs":"https://arxiv.org/abs/1811.07062v2","url_pdf":"https://arxiv.org/pdf/1811.07062v2.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":"the-full-spectrum-of-deep-net-hessians-at","repo_url":"https://github.com/AnonymousNIPS2019/DeepnetHessian","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"the-full-spectrum-of-deep-net-hessians-at","repo_url":"https://github.com/deep-lab/DeepnetHessian","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1811.07062","atlas_url":"https://app.syntology.ai/?focus=1811.07062","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}