{"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/tensorial-mixture-models","title":"Tensorial Mixture Models","arxiv_id":"1610.04167","date":"2016-10-13","proceeding":null,"authors":["Or Sharir","Ronen Tamari","Nadav Cohen","Amnon Shashua"],"abstract":"Casting neural networks in generative frameworks is a highly sought-after\nendeavor these days. Contemporary methods, such as Generative Adversarial\nNetworks, capture some of the generative capabilities, but not all. In\nparticular, they lack the ability of tractable marginalization, and thus are\nnot suitable for many tasks. Other methods, based on arithmetic circuits and\nsum-product networks, do allow tractable marginalization, but their performance\nis challenged by the need to learn the structure of a circuit. Building on the\ntractability of arithmetic circuits, we leverage concepts from tensor analysis,\nand derive a family of generative models we call Tensorial Mixture Models\n(TMMs). TMMs assume a simple convolutional network structure, and in addition,\nlend themselves to theoretical analyses that allow comprehensive understanding\nof the relation between their structure and their expressive properties. We\nthus obtain a generative model that is tractable on one hand, and on the other\nhand, allows effective representation of rich distributions in an easily\ncontrolled manner. These two capabilities are brought together in the task of\nclassification under missing data, where TMMs deliver state of the art\naccuracies with seamless implementation and design.","url_abs":"http://arxiv.org/abs/1610.04167v5","url_pdf":"http://arxiv.org/pdf/1610.04167v5.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":"tensorial-mixture-models","repo_url":"https://github.com/HUJI-Deep/Generative-ConvACs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"tensorial-mixture-models","repo_url":"https://github.com/HUJI-Deep/caffe-simnets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1610.04167","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}