{"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/pseudo-bayesian-learning-with-kernel-fourier","title":"Pseudo-Bayesian Learning with Kernel Fourier Transform as Prior","arxiv_id":"1810.12683","date":"2018-10-30","proceeding":null,"authors":["Gaël Letarte","Emilie Morvant","Pascal Germain"],"abstract":"We revisit Rahimi and Recht (2007)'s kernel random Fourier features (RFF)\nmethod through the lens of the PAC-Bayesian theory. While the primary goal of\nRFF is to approximate a kernel, we look at the Fourier transform as a prior\ndistribution over trigonometric hypotheses. It naturally suggests learning a\nposterior on these hypotheses. We derive generalization bounds that are\noptimized by learning a pseudo-posterior obtained from a closed-form\nexpression. Based on this study, we consider two learning strategies: The first\none finds a compact landmarks-based representation of the data where each\nlandmark is given by a distribution-tailored similarity measure, while the\nsecond one provides a PAC-Bayesian justification to the kernel alignment method\nof Sinha and Duchi (2016).","url_abs":"http://arxiv.org/abs/1810.12683v2","url_pdf":"http://arxiv.org/pdf/1810.12683v2.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":"pseudo-bayesian-learning-with-kernel-fourier","repo_url":"https://github.com/gletarte/pbrff","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"generalization-bounds","task_name":"Generalization Bounds"}],"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}