{"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/implicit-regularization-in-deep-learning-a","title":"Implicit Regularization via Neural Feature Alignment","arxiv_id":"2008.00938","date":"2020-08-03","proceeding":"NeurIPS Workshop DL-IG 2020 12","authors":["Aristide Baratin","Thomas George","César Laurent","R. Devon Hjelm","Guillaume Lajoie","Pascal Vincent","Simon Lacoste-Julien"],"abstract":"We approach the problem of implicit regularization in deep learning from a geometrical viewpoint. We highlight a regularization effect induced by a dynamical alignment of the neural tangent features introduced by Jacot et al, along a small number of task-relevant directions. This can be interpreted as a combined mechanism of feature selection and compression. By extrapolating a new analysis of Rademacher complexity bounds for linear models, we motivate and study a heuristic complexity measure that captures this phenomenon, in terms of sequences of tangent kernel classes along optimization paths.","url_abs":"https://arxiv.org/abs/2008.00938v3","url_pdf":"https://arxiv.org/pdf/2008.00938v3.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":"implicit-regularization-in-deep-learning-a","repo_url":"https://github.com/tfjgeorge/ntk_alignment","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"model-compression","task_name":"Model Compression"},{"task_slug":"feature-selection","task_name":"feature selection"}],"methods":[{"method_slug":"feature-selection","method_name":"Feature Selection"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2008.00938","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}