{"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/a-deep-and-tractable-density-estimator","title":"A Deep and Tractable Density Estimator","arxiv_id":"1310.1757","date":"2013-10-07","proceeding":null,"authors":["Benigno Uria","Iain Murray","Hugo Larochelle"],"abstract":"The Neural Autoregressive Distribution Estimator (NADE) and its real-valued\nversion RNADE are competitive density models of multidimensional data across a\nvariety of domains. These models use a fixed, arbitrary ordering of the data\ndimensions. One can easily condition on variables at the beginning of the\nordering, and marginalize out variables at the end of the ordering, however\nother inference tasks require approximate inference. In this work we introduce\nan efficient procedure to simultaneously train a NADE model for each possible\nordering of the variables, by sharing parameters across all these models. We\ncan thus use the most convenient model for each inference task at hand, and\nensembles of such models with different orderings are immediately available.\nMoreover, unlike the original NADE, our training procedure scales to deep\nmodels. Empirically, ensembles of Deep NADE models obtain state of the art\ndensity estimation performance.","url_abs":"http://arxiv.org/abs/1310.1757v2","url_pdf":"http://arxiv.org/pdf/1310.1757v2.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":"a-deep-and-tractable-density-estimator","repo_url":"https://github.com/princetonlips/mam","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"density-estimation","task_name":"Density Estimation"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-binarized-mnist","task":"Image Generation","dataset":"Binarized MNIST","model":"NADE","rank_in_archive_order":10,"of":10,"metrics":{"nats":"88.33"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1310.1757","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}