{"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/generative-moment-matching-networks","title":"Generative Moment Matching Networks","arxiv_id":"1502.02761","date":"2015-02-10","proceeding":null,"authors":["Yujia Li","Kevin Swersky","Richard Zemel"],"abstract":"We consider the problem of learning deep generative models from data. We\nformulate a method that generates an independent sample via a single\nfeedforward pass through a multilayer perceptron, as in the recently proposed\ngenerative adversarial networks (Goodfellow et al., 2014). Training a\ngenerative adversarial network, however, requires careful optimization of a\ndifficult minimax program. Instead, we utilize a technique from statistical\nhypothesis testing known as maximum mean discrepancy (MMD), which leads to a\nsimple objective that can be interpreted as matching all orders of statistics\nbetween a dataset and samples from the model, and can be trained by\nbackpropagation. We further boost the performance of this approach by combining\nour generative network with an auto-encoder network, using MMD to learn to\ngenerate codes that can then be decoded to produce samples. We show that the\ncombination of these techniques yields excellent generative models compared to\nbaseline approaches as measured on MNIST and the Toronto Face Database.","url_abs":"http://arxiv.org/abs/1502.02761v1","url_pdf":"http://arxiv.org/pdf/1502.02761v1.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":"generative-moment-matching-networks","repo_url":"https://github.com/yujiali/gmmn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"generative-moment-matching-networks","repo_url":"https://github.com/Abhipanda4/GMMN-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"generative-moment-matching-networks","repo_url":"https://github.com/siddharth-agrawal/Generative-Moment-Matching-Networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"hypothesis-testing","task_name":"Two-sample testing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1502.02761","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}