{"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/max-margin-deep-generative-models","title":"Max-margin Deep Generative Models","arxiv_id":"1504.06787","date":"2015-04-26","proceeding":"NeurIPS 2015 12","authors":["Chongxuan Li","Jun Zhu","Tianlin Shi","Bo Zhang"],"abstract":"Deep generative models (DGMs) are effective on learning multilayered\nrepresentations of complex data and performing inference of input data by\nexploring the generative ability. However, little work has been done on\nexamining or empowering the discriminative ability of DGMs on making accurate\npredictions. This paper presents max-margin deep generative models (mmDGMs),\nwhich explore the strongly discriminative principle of max-margin learning to\nimprove the discriminative power of DGMs, while retaining the generative\ncapability. We develop an efficient doubly stochastic subgradient algorithm for\nthe piecewise linear objective. Empirical results on MNIST and SVHN datasets\ndemonstrate that (1) max-margin learning can significantly improve the\nprediction performance of DGMs and meanwhile retain the generative ability; and\n(2) mmDGMs are competitive to the state-of-the-art fully discriminative\nnetworks by employing deep convolutional neural networks (CNNs) as both\nrecognition and generative models.","url_abs":"http://arxiv.org/abs/1504.06787v4","url_pdf":"http://arxiv.org/pdf/1504.06787v4.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":"max-margin-deep-generative-models","repo_url":"https://github.com/zhenxuan00/mmdgm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"max-margin-deep-generative-models","repo_url":"https://github.com/thu-ml/mmdcgm-ssl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}