{"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/convexified-convolutional-neural-networks","title":"Convexified Convolutional Neural Networks","arxiv_id":"1609.01000","date":"2016-09-04","proceeding":"ICML 2017 8","authors":["Yuchen Zhang","Percy Liang","Martin J. Wainwright"],"abstract":"We describe the class of convexified convolutional neural networks (CCNNs),\nwhich capture the parameter sharing of convolutional neural networks in a\nconvex manner. By representing the nonlinear convolutional filters as vectors\nin a reproducing kernel Hilbert space, the CNN parameters can be represented as\na low-rank matrix, which can be relaxed to obtain a convex optimization\nproblem. For learning two-layer convolutional neural networks, we prove that\nthe generalization error obtained by a convexified CNN converges to that of the\nbest possible CNN. For learning deeper networks, we train CCNNs in a layer-wise\nmanner. Empirically, CCNNs achieve performance competitive with CNNs trained by\nbackpropagation, SVMs, fully-connected neural networks, stacked denoising\nauto-encoders, and other baseline methods.","url_abs":"http://arxiv.org/abs/1609.01000v1","url_pdf":"http://arxiv.org/pdf/1609.01000v1.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":"convexified-convolutional-neural-networks","repo_url":"https://github.com/NMADALI97/Convexified-Convolutional-Neural-Networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1609.01000","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}